Merge branch 'sigma-pipeline-dir' into esql-correlations

EVTX Import cleanup

.github/workflows/pythontest.yml

@@ -6,6 +6,9 @@ on:
       - "salt/sensoroni/files/analyzers/**"
       - "salt/manager/tools/sbin/**"
       - "salt/_beacons/**"
+      - "salt/telegraf/tools/sbin_jinja/**"
+      - "salt/telegraf/defaults.yaml"
+      - "salt/telegraf/soc_telegraf.yaml"
 
 jobs:
   build:
@@ -34,3 +37,25 @@ jobs:
     - name: Test with pytest
       run: |
         PYTHONPATH=${{ matrix.python-code-path }} pytest ${{ matrix.python-code-path }} --cov=${{ matrix.python-code-path }} --doctest-modules --cov-report=term --cov-fail-under=100 --cov-config=pytest.ini
+
+  telegraf-collector:
+    # so-container-stats is a jinja template rather than an importable module, so it gets its
+    # own job: the test renders it the way salt does, then drives it with a faked docker engine
+    # and cgroup tree. No container runtime is needed.
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.14"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8 pytest jinja2 pyyaml
+    - name: Lint with flake8
+      run: |
+        flake8 salt/telegraf/tools/sbin_jinja/so-container-stats_test.py --config=pytest.ini
+    - name: Test with pytest
+      run: |
+        pytest salt/telegraf/tools/sbin_jinja/so-container-stats_test.py -v

salt/common/init.sls

@@ -117,14 +117,25 @@ elastic_curl_config:
 {% endif %}
 
 
+# A non-root owner here can chmod the directory and replace any script in it, including
+# the root-owned ones. 555 is the mode the filesystem RPM ships; root ignores it anyway.
+usr_sbin_perms:
+  file.directory:
+    - name: /usr/sbin
+    - user: root
+    - group: root
+    - mode: 555
+
 common_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - show_changes: False
+    - require:
+      - file: usr_sbin_perms
 {% if GLOBALS.role == 'so-heavynode' %}
     - exclude_pat:
       - so-pcap-import
@@ -159,8 +170,8 @@ common_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -173,6 +184,8 @@ so-status_script:
   file.managed:
     - name: /usr/sbin/so-status
     - source: salt://common/tools/sbin/so-status
+    - user: root
+    - group: root
     - mode: 755
 
 {% if GLOBALS.is_sensor %}
@@ -204,9 +217,11 @@ sostatus_log:
     - replace: False
 
 # Install sostatus check cron. This is used to populate Grid.
+# telegraf reads status.log on the same minute boundary this runs, so write aside and rename
+# rather than truncating the file it is reading
 so-status_check_cron:
   cron.present:
-    - name: '/usr/sbin/so-status -j > /opt/so/log/sostatus/status.log 2>&1'
+    - name: '/usr/sbin/so-status -j > /opt/so/log/sostatus/status.log.tmp 2>&1; mv -f /opt/so/log/sostatus/status.log.tmp /opt/so/log/sostatus/status.log'
     - identifier: so-status_check_cron
     - user: root
     - minute: '*/1'

salt/common/soup_scripts.sls

@@ -18,47 +18,61 @@ copy_so-common_common_tools_sbin:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-image-common_common_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_soup_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-firewall_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-yaml_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-repo-sync_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_bootstrap-salt_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/salt/scripts/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 644
 
 # This section is used to put the new script in place so that it can be called during soup.
 # It is faster than calling the states that normally manage them to put them in place.
@@ -67,46 +81,60 @@ copy_so-common_sbin:
     - name: /usr/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-image-common_sbin:
   file.copy:
     - name: /usr/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_soup_sbin:
   file.copy:
     - name: /usr/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-firewall_sbin:
   file.copy:
     - name: /usr/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-yaml_sbin:
   file.copy:
     - name: /usr/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-repo-sync_sbin:
   file.copy:
     - name: /usr/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_bootstrap-salt_sbin:
   file.copy:
     - name: /usr/sbin/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755

salt/common/tools/sbin/so-common

@@ -240,7 +240,8 @@ copy_new_files() {
   cd $UPDATE_DIR
   rsync -a salt $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
   rsync -a pillar $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
-  chown -R socore:socore $DEFAULT_SALT_DIR/
+  # Root-executed code; SOC only needs to read it. Local dirs stay socore-owned.
+  chown -R root:root $DEFAULT_SALT_DIR/
   cd /tmp
 }
 

salt/common/tools/sbin/so-common-status-check

@@ -9,6 +9,7 @@ import sys
 import subprocess
 import os
 import json
+import tempfile
 
 sys.path.append('/opt/saltstack/salt/lib/python3.10/site-packages/')
 import salt.config
@@ -17,6 +18,21 @@ import salt.loader
 __opts__ = salt.config.minion_config('/etc/salt/minion')
 __grains__ = salt.loader.grains(__opts__)
 
+def write_atomic(path, value):
+  # telegraf reads these files on its own schedule; replacing them by rename means it never
+  # reads a truncated file and reports an empty value as if it were real
+  directory = os.path.dirname(path)
+  handle, temp = tempfile.mkstemp(dir=directory)
+  try:
+    with os.fdopen(handle, 'w') as f:
+      f.write(str(value))
+    os.chmod(temp, 0o644)
+    os.replace(temp, path)
+  except Exception:
+    os.path.exists(temp) and os.unlink(temp)
+    raise
+
+
 def check_needs_restarted():
   osfam = __grains__['os_family']
   val = '0'
@@ -34,8 +50,7 @@ def check_needs_restarted():
   else:
     fail("Unsupported OS")
 
-  with open(outfile, 'w') as f:
-    f.write(val)
+  write_atomic(outfile, val)
 
 def check_for_fps():
     feat = 'fps'
@@ -56,8 +71,7 @@ def check_for_fps():
           # Unknown, so assume 0
           fps = 0
 
-    with open('/opt/so/log/sostatus/fps_enabled', 'w') as f:
-       f.write(str(fps))
+    write_atomic('/opt/so/log/sostatus/fps_enabled', fps)
 
 def check_for_lks():
     feat = 'Lks'
@@ -80,8 +94,7 @@ def check_for_lks():
                                 lks = 1
         if lks:
             break
-    with open('/opt/so/log/sostatus/lks_enabled', 'w') as f:
-       f.write(str(lks))
+    write_atomic('/opt/so/log/sostatus/lks_enabled', lks)
 
 def fail(msg):
   print(msg, file=sys.stderr)

salt/common/tools/sbin/so-log-check

@@ -177,6 +177,7 @@ if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Unexpected authorization header" # expected WARN log lines indicating invalid auth header
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Missing ory_kratos_session cookie" # expected WARN log lines indicating invalid auth header
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Static assets preprocessor only supports GET and HEAD requests" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|respondError"                 # respondError is a function name, output via http middleware as standard request logging
 fi
 
 if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
@@ -240,7 +241,7 @@ if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|marked for removal"           # docker container getting recycled
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|tcp 127.0.0.1:6791: bind: address already in use" # so-elastic-fleet agent restarting. Seen starting w/ 8.18.8 https://github.com/elastic/kibana/issues/201459
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|TransformTask\] \[logs-.*user so_kibana lacks the required permissions" # Known issue with integrations starting transform jobs that are explicitly not allowed to start as a system user
-    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # appears in so-dockerregistry log for so-tcpreplay following docker upgrade to 29.2.1-1
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # so-dockerregistry logs a tag lookup miss during image copy; not tied to one docker version
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Could not index event to Elasticsearch.*\"version\" => \"9.0.8\"" # Expected during Elastic upgrade temporarily, as policies referencing older pipelines are updated
 fi
 

salt/common/tools/sbin_jinja/so-raid-status

@@ -125,4 +125,6 @@ else
   RAIDSTATUS=1
 fi
 
-echo "nsmraid=$RAIDSTATUS" > /opt/so/log/raid/status.log
+# telegraf reads this file; write aside and rename so it never sees a half-written file
+echo "nsmraid=$RAIDSTATUS" > /opt/so/log/raid/status.log.tmp
+mv -f /opt/so/log/raid/status.log.tmp /opt/so/log/raid/status.log

salt/docker/defaults.yaml

@@ -1,6 +1,12 @@
 docker:
   range: '172.17.1.0/24'
   gateway: '172.17.1.1'
+  networks:
+    sobridge: {}
+    soauth:
+      range: '172.17.2.0/24'
+      gateway: '172.17.2.1'
+      manager_only: True
   ulimits:
     - name: nofile
       soft: 1048576
@@ -58,18 +64,18 @@ docker:
       ulimits: []
     'so-kratos':
       final_octet: 28
+      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4433:4433
-        - 0.0.0.0:4434:4434
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
       ulimits: []
     'so-hydra':
       final_octet: 30
+      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4444:4444
-        - 0.0.0.0:4445:4445
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
@@ -128,6 +134,7 @@ docker:
       ulimits: []
     'so-soc':
       final_octet: 34
+      networks: ['sobridge', 'soauth']
       port_bindings:
         - 0.0.0.0:9822:9822
       custom_bind_mounts: []

salt/docker/docker.map.jinja

@@ -1,8 +1,26 @@
 {% import_yaml 'docker/defaults.yaml' as DOCKERDEFAULTS %}
 {% set DOCKERMERGED = salt['pillar.get']('docker', DOCKERDEFAULTS.docker, merge=True) %}
-{% set RANGESPLIT = DOCKERMERGED.range.split('.') %}
-{% set FIRSTTHREE = RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.' %}
+
+{% if DOCKERMERGED.networks.sobridge is not mapping %}
+{%   do DOCKERMERGED.networks.update({'sobridge': {}}) %}
+{% endif %}
+{% do DOCKERMERGED.networks['sobridge'].update({'range': DOCKERMERGED.range, 'gateway': DOCKERMERGED.gateway}) %}
+
+{% for netname, net in DOCKERMERGED.networks.items() %}
+{%   set RANGESPLIT = net.range.split('.') %}
+{%   do net.update({'prefix': RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.'}) %}
+{% endfor %}
 
 {% for container, vals in DOCKERMERGED.containers.items() %}
-{%   do DOCKERMERGED.containers[container].update({'ip': FIRSTTHREE ~ DOCKERMERGED.containers[container].final_octet}) %}
+{%   set CONTAINER_NETS = vals.get('networks', ['sobridge']) %}
+{%   set IPS = {} %}
+{%   for netname in CONTAINER_NETS %}
+{%     do IPS.update({netname: DOCKERMERGED.networks[netname].prefix ~ vals.final_octet}) %}
+{%   endfor %}
+{%   do DOCKERMERGED.containers[container].update({
+         'networks': CONTAINER_NETS,
+         'ips': IPS,
+         'network': CONTAINER_NETS[0],
+         'ip': IPS[CONTAINER_NETS[0]]
+       }) %}
 {% endfor %}

salt/docker/init.sls

@@ -18,10 +18,10 @@ dockergroup:
 dockerheldpackages:
   pkg.installed:
     - pkgs:
-      - containerd.io: 2.2.1-1.el9
-      - docker-ce: 3:29.2.1-1.el9
-      - docker-ce-cli: 1:29.2.1-1.el9
-      - docker-ce-rootless-extras: 29.2.1-1.el9
+      - containerd.io: 2.3.6-1.el9
+      - docker-ce: 3:29.8.1-1.el9
+      - docker-ce-cli: 1:29.8.1-1.el9
+      - docker-ce-rootless-extras: 29.8.1-1.el9
     - hold: True
     - update_holds: True
 
@@ -71,15 +71,19 @@ dockerreserveports:
     - source: salt://common/files/99-reserved-ports.conf
     - name: /etc/sysctl.d/99-reserved-ports.conf
 
-sos_docker_net:
+{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{% if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+sos_docker_net_{{ NETNAME }}:
   docker_network.present:
-    - name: sobridge
-    - subnet: {{ DOCKERMERGED.range }}
-    - gateway: {{ DOCKERMERGED.gateway }}
+    - name: {{ NETNAME }}
+    - subnet: {{ NETWORK.range }}
+    - gateway: {{ NETWORK.gateway }}
     - options:
-        com.docker.network.bridge.name: 'sobridge'
+        com.docker.network.bridge.name: '{{ NETNAME }}'
         com.docker.network.driver.mtu: '1500'
         com.docker.network.bridge.enable_ip_masquerade: 'true'
         com.docker.network.bridge.enable_icc: 'true'
         com.docker.network.bridge.host_binding_ipv4: '0.0.0.0'
-    - unless: ip l | grep sobridge
+    - unless: ip l | grep {{ NETNAME }}
+{% endif %}
+{% endfor %}

salt/docker/soc_docker.yaml

@@ -7,6 +7,40 @@ docker:
     description: Default docker IP range for containers.
     helpLink: docker
     advanced: True
+  networks:
+    sobridge:
+      description: |
+        The default docker network, carrying most containers. Its range and gateway are taken
+        from the docker.range and docker.gateway settings above rather than set here.
+      helpLink: docker
+      readonly: True
+      advanced: True
+      global: True
+    soauth:
+      range:
+        description: |
+          IP range for the soauth docker network, an isolated network for the authentication
+          services, so that the Kratos and Hydra admin APIs are only reachable from the
+          containers placed on it.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+      gateway:
+        description: Gateway for the soauth docker network.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+      manager_only:
+        description: |
+          Limits the soauth network to grid members running the authentication containers,
+          instead of creating it on every node.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+        forcedType: bool
   ulimits:
     description: |
       Default ulimit settings applied to all containers via the Docker daemon. Each entry specifies a resource name (e.g. nofile, memlock, core, nproc) with soft and hard limits. Individual container ulimits override these defaults. Valid resource names include: cpu, fsize, data, stack, core, rss, nproc, nofile, memlock, as, locks, sigpending, msgqueue, nice, rtprio, rttime.
@@ -34,6 +68,16 @@ docker:
         readonly: True
         advanced: True
         global: True
+      networks:
+        description: |
+          Docker networks this container is attached to. The first entry is the container's
+          primary network and determines the address its published ports are forwarded to.
+          Defaults to sobridge when unset.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+        forcedType: "[]string"
       port_bindings:
         description: List of port bindings for the container.
         helpLink: docker

salt/elastalert/config.sls

@@ -21,6 +21,7 @@ elastalert:
     - gid: 933
     - home: /opt/so/conf/elastalert
     - createhome: False
+    - shell: /sbin/nologin
 
 elastalogdir:
   file.directory:
@@ -33,8 +34,8 @@ elastalert_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elastalert/tools/sbin
-    - user: 933
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #elastalert_sbin_jinja:

salt/elastalert/defaults.yaml

@@ -10,7 +10,7 @@ elastalert:
     buffer_time:
       minutes: 10
     old_query_limit:
-      minutes: 5
+      minutes: 1440
     es_port: 9200
     es_conn_timeout: 55
     max_query_size: 5000

salt/elastalert/files/modules/so/securityonion-es.py

@@ -6,9 +6,14 @@
 # Elastic License 2.0.
 
 
+from datetime import datetime
 from time import gmtime, strftime
+import hashlib
+import ipaddress
+import re
 import requests,json
-from elastalert.alerts import Alerter
+from elastalert.alerts import Alerter, DateTimeEncoder
+from elastalert.util import EAException, elastalert_logger
 
 import urllib3
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
@@ -19,17 +24,152 @@ class SecurityOnionESAlerter(Alerter):
     """
 
     required_options = set(['detection_title', 'sigma_level'])
-    optional_fields = ['sigma_category', 'sigma_product', 'sigma_service']
+    optional_fields = ['sigma_category', 'sigma_product', 'sigma_service', 'sigma_correlation']
+
+    count_labels = {
+        'event_count': '%count% events',
+        'value_count': '%count% distinct values',
+        'event_type_count': '%count% correlated rules matched',
+        'value_sum': 'total %count%',
+        'value_avg': 'average %count%',
+        'value_percentile': 'percentile %count%',
+        'value_median': 'median %count%',
+    }
+    placeholder = re.compile(r'%([^%\s]+)%')
+    # group-by fields copied into ECS related.*
+    related_users = {'user.name', 'winlog.event_data.TargetUserName', 'winlog.event_data.SubjectUserName'}
+    related_hosts = {'host.name', 'host.hostname', 'winlog.computer_name'}
+
+    @staticmethod
+    def lookup(doc, dotted):
+        """ Resolve a dotted path; ES|QL columns arrive nested. """
+        node = doc
+        for part in dotted.split('.'):
+            if not isinstance(node, dict) or part not in node:
+                return None
+            node = node[part]
+        return node
+
+    def query_keys(self):
+        """ compound_query_key holds the list; query_key is flattened to a string. """
+        return self.rule.get('compound_query_key') or ([self.rule['query_key']] if self.rule.get('query_key') else [])
+
+    @staticmethod
+    def is_correlation(match):
+        """ Only correlation rows carry window_start, from the ES|QL stats. """
+        return 'window_start' in match
+
+    def alert_id(self, match):
+        """ Stable id: window end + group values for correlations, source _id otherwise. """
+        if self.is_correlation(match):
+            # ungrouped rows have a hashed _id that changes with the count
+            values = ''.join(f"|{self.lookup(match, k)}" for k in self.query_keys())
+            key = f"{self.rule['detection_public_id']}|{self.to_dt(match['@timestamp']).isoformat()}{values}"
+        else:
+            key = f"{self.rule['detection_public_id']}|{match.get('_id')}"
+
+        return hashlib.sha256(key.encode('utf-8')).hexdigest()
+
+    def group(self, match):
+        """ Group-by values joined as ElastAlert joins them for the realert silence key. """
+        return ', '.join(str(self.lookup(match, k)) for k in self.query_keys())
+
+    def related_bucket(self, key):
+        if key == 'ip' or key.endswith('.ip'):
+            return 'ip'
+        if key in self.related_users or key.endswith('.user.name'):
+            return 'user'
+        if key in self.related_hosts:
+            return 'hosts'
+        return None
+
+    @staticmethod
+    def valid_ip(value):
+        try:
+            ipaddress.ip_address(value)
+            return True
+        except ValueError:
+            return False
+
+    def related(self, match):
+        """ ECS related.* from group-by values; invalid IPs are skipped, as they fail the ip mapping. """
+        related = {}
+        for key in self.query_keys():
+            bucket = self.related_bucket(key)
+            if not bucket:
+                continue
+            value = self.lookup(match, key)
+            for v in value if isinstance(value, list) else [value]:
+                if v is None or (bucket == 'ip' and not self.valid_ip(str(v))):
+                    continue
+                related.setdefault(bucket, {})[str(v)] = None
+        return {bucket: list(values) for bucket, values in related.items()}
+
+    def event_data(self, match):
+        """ The match without the compound query_key field, which ES would map by its last part (e.g. .ip). """
+        if not self.rule.get('compound_query_key'):
+            return match
+        return {k: v for k, v in match.items() if k != self.rule['query_key']}
+
+    @staticmethod
+    def format_value(value):
+        if isinstance(value, list):
+            shown = ', '.join(str(v) for v in value[:3])
+            return shown if len(value) <= 3 else f"{shown} and {len(value) - 3} more"
+        return str(value)
+
+    @staticmethod
+    def format_count(value):
+        if isinstance(value, float) and not value.is_integer():
+            return f"{value:,.2f}"
+        if isinstance(value, (int, float)):
+            return f"{int(value):,}"
+        return str(value)
+
+    @staticmethod
+    def format_duration(seconds):
+        for unit, size in (('hour', 3600), ('minute', 60)):
+            if seconds >= 2 * size:
+                return f"{seconds // size} {unit}s"
+        return f"{seconds} second{'' if seconds == 1 else 's'}"
+
+    @staticmethod
+    def to_dt(value):
+        # ES|QL gives ISO strings; ElastAlert parses @timestamp, except on a retried alert.
+        return value if isinstance(value, datetime) else datetime.fromisoformat(value)
+
+    def summary(self, match):
+        """ One-line correlation summary; None for single-event rules. """
+        if not self.is_correlation(match):
+            return None
+
+        start = self.to_dt(match['window_start'])
+        end = self.to_dt(match['@timestamp'])
+        name = next((f for f in self.count_labels if f in match), None)
+        values = {
+            'count': self.format_count(match.get(name)),
+            'start': start.strftime('%Y-%m-%d %H:%M:%S UTC'),
+            'end': end.strftime('%Y-%m-%d %H:%M:%S UTC'),
+            'duration': self.format_duration(int((end - start).total_seconds())),
+        }
+
+        template = self.rule.get('summary_template')
+        if not template:
+            groups = ', '.join(f"{k} %{k}%" for k in self.query_keys())
+            template = f"{self.count_labels.get(name, '%count%')}{' for ' + groups if groups else ''} in %duration%"
+
+        def fill(m):
+            if m[1] in values:
+                return values[m[1]]
+            value = self.lookup(match, m[1])
+            # unknown placeholders stay visible so typos show
+            return m[0] if value is None else self.format_value(value)
+
+        return self.placeholder.sub(fill, template)
 
     def alert(self, matches):
         for match in matches:
             timestamp = strftime("%Y-%m-%d"'T'"%H:%M:%S"'.000Z', gmtime())
-            headers = {"Content-Type": "application/json"}
-
-            creds = None
-            if 'es_username' in self.rule and 'es_password' in self.rule:
-                creds = (self.rule['es_username'], self.rule['es_password'])
-
             # Start building the rule dict
             rule_info = {
                 "name": self.rule['detection_title'],
@@ -42,22 +182,74 @@ class SecurityOnionESAlerter(Alerter):
                 if field in self.rule:
                     rule_info[rule_key] = self.rule[field]
 
+            event_info = {
+                "kind": "alert",
+                "severity": self.rule['event.severity'],
+                "module": self.rule['event.module'],
+                "dataset": self.rule['event.dataset'],
+                "severity_label": self.rule['sigma_level']
+            }
+
+            reason = self.summary(match)
+            if reason:
+                event_info["reason"] = reason
+
             # Construct the payload with the conditional rule_info
             payload = {
-                "tags": "alert",
+                "tags": ["alert"],
                 "rule": rule_info,
-                "event": {
-                    "severity": self.rule['event.severity'],
-                    "module": self.rule['event.module'],
-                    "dataset": self.rule['event.dataset'],
-                    "severity_label": self.rule['sigma_level']
-                },
+                "event": event_info,
                 "sigma_level": self.rule['sigma_level'],
-                "event_data": match,
+                "event_data": self.event_data(match),
                 "@timestamp": timestamp
             }
-            url = f"https://{self.rule['es_host']}:{self.rule['es_port']}/logs-detections.alerts-so/_doc/"
-            requests.post(url, data=json.dumps(payload), headers=headers, verify=False, auth=creds)
+
+            keys = self.query_keys()
+            if keys and self.is_correlation(match):
+                payload["labels"] = {
+                    "correlation_group_by": ', '.join(keys),
+                    "correlation_group": self.group(match),
+                }
+                related = self.related(match)
+                if related:
+                    payload["related"] = related
+            alert_id = self.alert_id(match)
+            # _create returns 409 on a repeat id; EAException makes ElastAlert retry
+            url = (f"https://{self.rule['es_host']}:{self.rule['es_port']}"
+                   f"/logs-detections.alerts-so/_create/{alert_id}")
+            response = self.put_alert(url, payload)
+            if response.status_code == 400:
+                # mapping rejections come from event_data; retry with it as unindexed text
+                rejection = response.text[:500]
+                payload = self.without_event_data(payload, rejection)
+                response = self.put_alert(url, payload)
+                if response.status_code == 400:
+                    elastalert_logger.error("Dropping alert %s for rule %s, rejected by Elasticsearch even without its event data: %s; first rejection: %s",
+                                            alert_id, self.rule['detection_public_id'], response.text[:500], rejection)
+                    continue
+                elastalert_logger.warning("Stored alert %s for rule %s with its event data as text, rejected by Elasticsearch: %s",
+                                          alert_id, self.rule['detection_public_id'], rejection)
+            if response.status_code != 409 and not response.ok:
+                raise EAException(f"Unable to write alert: {response.status_code} {response.text[:500]}")
+
+    def put_alert(self, url, payload):
+        creds = None
+        if 'es_username' in self.rule and 'es_password' in self.rule:
+            creds = (self.rule['es_username'], self.rule['es_password'])
+        try:
+            return requests.put(url, data=json.dumps(payload, cls=DateTimeEncoder),
+                                headers={"Content-Type": "application/json"}, verify=False, auth=creds)
+        except requests.RequestException as e:
+            raise EAException(f"Unable to write alert: {e}")
+
+    @staticmethod
+    def without_event_data(payload, rejection):
+        """ event_data moved to event.original; the tag keeps Fleet's final pipeline from removing it. """
+        fallback = {k: v for k, v in payload.items() if k != 'event_data'}
+        fallback['event'] = dict(payload['event'], original=json.dumps(payload['event_data'], cls=DateTimeEncoder))
+        fallback['error'] = {'message': f"event_data rejected by Elasticsearch: {rejection}"}
+        fallback['tags'] = payload['tags'] + ['preserve_original_event']
+        return fallback
 
     def get_info(self):
         return {'type': 'SecurityOnionESAlerter'}

salt/elastalert/files/modules/so/securityonion-es_test.py

@@ -0,0 +1,211 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+import copy
+from datetime import datetime, timezone
+import importlib.util
+import json
+import logging
+import os
+import sys
+import types
+import unittest
+from unittest.mock import MagicMock, patch
+
+# Real ElastAlert when installed (so-elastalert); otherwise stand-ins for what the alerter imports.
+try:
+    import elastalert.alerts  # noqa: F401
+except ImportError:
+
+    class Alerter:
+        def __init__(self, rule):
+            self.rule = rule
+
+    class DateTimeEncoder(json.JSONEncoder):
+        def default(self, obj):
+            return obj.isoformat() if hasattr(obj, 'isoformat') else json.JSONEncoder.default(self, obj)
+
+    class EAException(Exception):
+        pass
+
+    alerts = types.ModuleType('elastalert.alerts')
+    alerts.Alerter = Alerter
+    alerts.DateTimeEncoder = DateTimeEncoder
+    util = types.ModuleType('elastalert.util')
+    util.EAException = EAException
+    util.elastalert_logger = logging.getLogger('elastalert')
+    package = types.ModuleType('elastalert')
+    package.alerts = alerts
+    package.util = util
+    sys.modules.update({'elastalert': package, 'elastalert.alerts': alerts, 'elastalert.util': util})
+
+spec = importlib.util.spec_from_file_location('securityonion_es', os.path.join(os.path.dirname(__file__), 'securityonion-es.py'))
+es = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(es)
+
+BASE_RULE = {
+    'name': 'Many Failed Network Logons To One Host From One Source -- 35a42db6-6629-45af-b8aa-e1fa33c28ef5',
+    'detection_title': 'Many Failed Network Logons To One Host From One Source',
+    'detection_public_id': '35a42db6-6629-45af-b8aa-e1fa33c28ef5',
+    'sigma_level': 'medium',
+    'sigma_correlation': 'event_count',
+    'event.severity': 3,
+    'event.module': 'sigma',
+    'event.dataset': 'sigma.alert',
+    'es_host': 'manager',
+    'es_port': 9200,
+    'summary_template': '%count% failed network logons to %host.name% from %source.ip% in %duration%',
+}
+
+
+def correlation_match():
+    return {
+        'event_count': 3561,
+        'window_start': '2026-09-30T18:05:10+00:00',
+        '@timestamp': '2026-09-30T18:07:53+00:00',
+        'host': {'name': 'sa-delta-02-jb'},
+        'source': {'ip': '192.168.198.149'},
+        '_id': '6d1c',
+        'num_hits': 1,
+        'num_matches': 1,
+    }
+
+
+class TestSecurityOnionESAlerter(unittest.TestCase):
+
+    def send(self, rule, match):
+        """ Run alert() and return the payload it wrote and the URL it wrote to. """
+        alerter = es.SecurityOnionESAlerter(rule)
+        response = MagicMock(status_code=201, ok=True)
+        with patch.object(es.requests, 'put', return_value=response) as put:
+            alerter.alert([match])
+        self.assertEqual(put.call_count, 1)
+        return json.loads(put.call_args.kwargs['data']), put.call_args.args[0]
+
+    def test_compound_query_key_left_out_of_event_data(self):
+        rule = dict(BASE_RULE, compound_query_key=['host.name', 'source.ip'], query_key='host.name,source.ip')
+        match = correlation_match()
+        match['host.name,source.ip'] = 'sa-delta-02-jb, 192.168.198.149'
+        original = copy.deepcopy(match)
+
+        payload, _ = self.send(rule, match)
+
+        self.assertNotIn('host.name,source.ip', payload['event_data'])
+        self.assertEqual(payload['event_data']['host'], {'name': 'sa-delta-02-jb'})
+        self.assertEqual(payload['event_data']['source'], {'ip': '192.168.198.149'})
+        self.assertEqual(payload['labels'], {'correlation_group_by': 'host.name, source.ip', 'correlation_group': 'sa-delta-02-jb, 192.168.198.149'})
+        self.assertEqual(payload['related'], {'hosts': ['sa-delta-02-jb'], 'ip': ['192.168.198.149']})
+        self.assertEqual(payload['event']['kind'], 'alert')
+        self.assertEqual(payload['event']['reason'], '3,561 failed network logons to sa-delta-02-jb from 192.168.198.149 in 2 minutes')
+        # ElastAlert reuses the match
+        self.assertEqual(match, original)
+
+    def test_single_query_key(self):
+        rule = dict(BASE_RULE, query_key='user.name', summary_template='%count% failed SOC logins for %user.name%')
+        match = {'event_count': 3, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
+                 'user': {'name': 'josh@local.invalid'}}
+
+        payload, _ = self.send(rule, match)
+
+        self.assertEqual(payload['labels'], {'correlation_group_by': 'user.name', 'correlation_group': 'josh@local.invalid'})
+        self.assertEqual(payload['related'], {'user': ['josh@local.invalid']})
+        self.assertEqual(payload['event']['reason'], '3 failed SOC logins for josh@local.invalid')
+        self.assertEqual(payload['event_data'], match)
+
+    def test_related_buckets(self):
+        rule = dict(BASE_RULE, compound_query_key=['winlog.event_data.TargetUserName', 'source.ip', 'dns.highest_registered_domain'],
+                    query_key='winlog.event_data.TargetUserName,source.ip,dns.highest_registered_domain')
+        match = correlation_match()
+        match.update({'winlog': {'event_data': {'TargetUserName': ['admmig', 'svc', 'admmig']}},
+                      'source': {'ip': 'not-an-ip'}, 'dns': {'highest_registered_domain': 'example.com'}})
+
+        payload, _ = self.send(rule, match)
+
+        # deduped; invalid IP skipped; domain stays in the group only
+        self.assertEqual(payload['related'], {'user': ['admmig', 'svc']})
+        self.assertEqual(payload['labels']['correlation_group'], "['admmig', 'svc', 'admmig'], not-an-ip, example.com")
+
+        payload, _ = self.send(dict(BASE_RULE, query_key='dns.highest_registered_domain'), match)
+
+        self.assertNotIn('related', payload)
+
+    def test_plain_rule_has_no_correlation_fields(self):
+        # a query_key alone, as from an override, does not make a correlation
+        rule = dict(BASE_RULE, query_key='user.name')
+        # ElastAlert parses @timestamp for EQL hits
+        match = {'@timestamp': datetime(2026, 9, 30, 16, 50, tzinfo=timezone.utc), '_id': 'abc',
+                 'process': {'name': 'whoami.exe'}, 'user': {'name': 'josh'}}
+
+        payload, url = self.send(rule, match)
+
+        alerter = es.SecurityOnionESAlerter(rule)
+        self.assertNotIn('labels', payload)
+        self.assertNotIn('related', payload)
+        self.assertNotIn('reason', payload['event'])
+        self.assertEqual(payload['event']['kind'], 'alert')
+        self.assertEqual(payload['event_data'], dict(match, **{'@timestamp': '2026-09-30T16:50:00+00:00'}))
+        self.assertTrue(url.endswith('/' + alerter.alert_id(match)))
+        self.assertNotEqual(alerter.alert_id(match), alerter.alert_id(dict(match, _id='abd')))
+
+    def test_ungrouped_correlation_id_ignores_row_hash(self):
+        rule = dict(BASE_RULE, summary_template=None)
+        first = {k: v for k, v in correlation_match().items() if k not in ('host', 'source')}
+        # ES|QL hashes the row into _id, so a later count changes it
+        later = dict(first, event_count=3600, _id='9f2a')
+
+        payload, url = self.send(rule, first)
+
+        alerter = es.SecurityOnionESAlerter(rule)
+        self.assertEqual(alerter.alert_id(first), alerter.alert_id(later))
+        self.assertNotEqual(alerter.alert_id(first), alerter.alert_id(dict(first, **{'@timestamp': '2026-09-30T18:09:00+00:00'})))
+        self.assertTrue(url.endswith('/' + alerter.alert_id(first)))
+        self.assertEqual(payload['event']['reason'], '3,561 events in 2 minutes')
+        self.assertNotIn('labels', payload)
+
+    def test_grouped_correlation_id_unchanged(self):
+        """ Ids of alerts already written must not change. """
+        rule = dict(BASE_RULE, compound_query_key=['host.name', 'source.ip'], query_key='host.name,source.ip')
+        key = f"{BASE_RULE['detection_public_id']}|2026-09-30T18:07:53+00:00|sa-delta-02-jb|192.168.198.149"
+
+        self.assertEqual(es.SecurityOnionESAlerter(rule).alert_id(correlation_match()), es.hashlib.sha256(key.encode()).hexdigest())
+
+    def send_responses(self, rule, match, responses):
+        """ Run alert() against a sequence of write responses; return the payloads written. """
+        alerter = es.SecurityOnionESAlerter(rule)
+        with patch.object(es.requests, 'put', side_effect=responses) as put:
+            alerter.alert([match])
+        return [json.loads(c.kwargs['data']) for c in put.call_args_list]
+
+    def test_rejected_event_data_is_kept_as_text(self):
+        rule = dict(BASE_RULE, query_key='user.name', summary_template='%count% failed SOC logins for %user.name%')
+        match = {'event_count': 3, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
+                 'user': {'name': 'josh@local.invalid'}}
+        rejected = MagicMock(status_code=400, ok=False, text='{"error":{"type":"document_parsing_exception"}}')
+
+        first, second = self.send_responses(rule, match, [rejected, MagicMock(status_code=201, ok=True)])
+
+        self.assertIn('event_data', first)
+        self.assertNotIn('event_data', second)
+        self.assertEqual(json.loads(second['event']['original']), match)
+        self.assertEqual(second['tags'], ['alert', 'preserve_original_event'])
+        self.assertEqual(first['tags'], ['alert'])
+        self.assertTrue(second['error']['message'].startswith('event_data rejected by Elasticsearch: {"error"'))
+        # everything else carries over
+        self.assertEqual({k: v for k, v in second['event'].items() if k != 'original'}, first['event'])
+        changed = ('event_data', 'event', 'error', 'tags')
+        self.assertEqual({k: v for k, v in second.items() if k not in changed}, {k: v for k, v in first.items() if k not in changed})
+
+    def test_rejected_twice_is_dropped_without_retry(self):
+        rejected = MagicMock(status_code=400, ok=False, text='{"error":{"type":"document_parsing_exception"}}')
+        match = {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'}
+
+        # no EAException, so no retry
+        payloads = self.send_responses(dict(BASE_RULE), match, [rejected, rejected])
+
+        self.assertEqual(len(payloads), 2)
+
+
+if __name__ == '__main__':
+    unittest.main()

salt/elastalert/soc_elastalert.yaml

@@ -120,7 +120,7 @@ elastalert:
         helpLink: elastalert
     old_query_limit:
       minutes:
-        description: Amount of time in minutes between queries to start at the most recently run query.
+        description: How long ElastAlert can be down, in minutes, and still resume each rule where it stopped. After a longer outage, rules restart from now and skip the gap.
         global: True
         helpLink: elastalert
     es_conn_timeout:

salt/elastic-fleet-package-registry/config.sls

@@ -19,6 +19,7 @@ elastic-agent-pr:
     - gid: 948
     - home: /opt/so/conf/elastic-fleet-pr
     - createhome: False
+    - shell: /sbin/nologin
 
 {% else %}
 

salt/elasticagent/config.sls

@@ -20,6 +20,7 @@ elastic-agent:
     - gid: 949
     - home: /opt/so/conf/elastic-agent
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticagentconfdir:
   file.directory:
@@ -39,8 +40,8 @@ elasticagent_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticagent/tools/sbin_jinja
-    - user: 949
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
 

salt/elasticfleet/config.sls

@@ -26,13 +26,14 @@ elastic-fleet:
     - gid: 947
     - home: /opt/so/conf/elastic-fleet
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticfleet_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - show_changes: False
 
@@ -40,8 +41,8 @@ elasticfleet_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin_jinja
-    - user: 947
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -81,8 +82,8 @@ eapackageupgrade:
   file.managed:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
     - source: salt://elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-upgrade
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - mode: 755
     - template: jinja
 

salt/elasticfleet/files/integrations/grid-nodes_general/import-evtx-logs.json

@@ -29,7 +29,7 @@
               "\\.gz$"
             ],
             "include_files": [],
-            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.22.3\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.9.0\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.22.3\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.22.3\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.9.0\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
+            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- add_fields:\n    target: event\n    fields:\n      dataset: windows.forwarded\n      module: windows\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: import.evtx\n- if:\n    equals:\n      winlog.channel: 'Security'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.security\n          module: system\n- if:\n    equals:\n      winlog.channel: 'Windows PowerShell'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell\n          module: windows\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n          module: system\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n          module: system\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n- add_fields:\n    target: data_stream\n    fields:\n        type: logs\n        dataset: import",
             "tags": [
               "import"
             ],

salt/elasticfleet/install_agent_grid.sls

@@ -14,8 +14,8 @@ so-elastic-agent-install:
   file.managed:
     - name: /usr/sbin/so-elastic-agent-install
     - source: salt://elasticfleet/tools/sbin/so-elastic-agent-install
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - mode: 755
     - show_changes: False
 

salt/elasticfleet/integration-defaults.map.jinja

@@ -30,17 +30,14 @@
     'azure_metrics.monitor': 'azure.monitor',
     'azure_metrics.storage_account': 'azure.storage_account',
     'azure_openai.metrics': 'azure.open_ai',
-    'beat.state': 'beats.stack_monitoring.state',
-    'beat.stats': 'beats.stack_monitoring.stats',
-    'enterprisesearch.health': 'enterprisesearch.stack_monitoring.health',
-    'enterprisesearch.stats': 'enterprisesearch.stack_monitoring.stats',
     'kibana.cluster_actions': 'kibana.stack_monitoring.cluster_actions',
     'kibana.cluster_rules': 'kibana.stack_monitoring.cluster_rules',
     'kibana.node_actions': 'kibana.stack_monitoring.node_actions',
     'kibana.node_rules': 'kibana.stack_monitoring.node_rules',
     'kibana.stats': 'kibana.stack_monitoring.stats',
     'kibana.status': 'kibana.stack_monitoring.status',
-    'logstash.node_cel': 'logstash.stack_monitoring.node',
+    'logstash.node': 'logstash.stack_monitoring.node',
+    'logstash.node_cel': 'logstash.node',
     'logstash.node_stats': 'logstash.stack_monitoring.node_stats',
     'synthetics.browser': 'synthetics-browser',
     'synthetics.browser_network': 'synthetics-browser.network',

salt/elasticfleet/tools/sbin/so-elastic-fleet-common

@@ -30,6 +30,56 @@ fleet_api() {
     curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/${QUERYPATH}" "$@" --retry 3 --retry-delay 10 --fail 2>/dev/null
 }
 
+elastic_fleet_require_agent_policy() {
+    local AGENT_POLICY=$1
+    local POLICY_JSON
+
+    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY") || [ -z "$POLICY_JSON" ]; then
+        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
+        return 1
+    fi
+
+    if ! jq -e '.item.package_policies | type == "array"' <<<"$POLICY_JSON" >/dev/null 2>&1; then
+        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
+        return 1
+    fi
+
+    echo "$POLICY_JSON"
+}
+
+# Print the single active enrollment token for POLICY_ID.
+# Exit 1: retryable (API failure, invalid response, no active token)
+# Exit 2: multiple active tokens - Shouldn't get into this state without manual intervention
+elastic_fleet_active_enrollment_token() {
+    local POLICY_ID=$1
+    local RESP TOKEN_COUNT API_KEY
+
+    if ! RESP=$(fleet_api "enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+        echo "Error: Failed to retrieve enrollment tokens for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    if ! jq -e '.list' <<<"$RESP" >/dev/null 2>&1; then
+        echo "Error: Invalid enrollment token response for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    TOKEN_COUNT=$(jq --arg pid "$POLICY_ID" '[.list[] | select(.policy_id == $pid and .active == true)] | length' <<<"$RESP")
+
+    if [ "${TOKEN_COUNT:-0}" -eq 0 ]; then
+        echo "Error: No active enrollment token found for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    if [ "$TOKEN_COUNT" -gt 1 ]; then
+        echo "Error: Found $TOKEN_COUNT active enrollment tokens for agent policy '$POLICY_ID'; expected exactly one." >&2
+        return 2
+    fi
+
+    API_KEY=$(jq -r --arg pid "$POLICY_ID" '.list[] | select(.policy_id == $pid and .active == true) | .api_key' <<<"$RESP")
+    echo "$API_KEY"
+}
+
 # Max number of concurrent Fleet write jobs (create/update). Override via env if needed.
 MAX_FLEET_JOBS=${MAX_FLEET_JOBS:-10}
 
@@ -62,15 +112,7 @@ elastic_fleet_load_integrations_dir() {
     i=0
 
     # Fetch the agent policy a single time; we look up integration ids locally below.
-    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY"); then
-        echo "Error: Failed to retrieve agent policy '$AGENT_POLICY'."
-        rm -f "$FAIL_FILE"
-        rm -rf "$OUT_DIR"
-        return 1
-    fi
-
-    if ! jq -e '.item.package_policies' <<<"$POLICY_JSON" >/dev/null 2>&1; then
-        echo "Error: Invalid agent policy response for '$AGENT_POLICY'."
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
         rm -f "$FAIL_FILE"
         rm -rf "$OUT_DIR"
         return 1
@@ -124,9 +166,15 @@ elastic_fleet_integration_check() {
 
     JSON_STRING=$2
 
-    NAME=$(jq -r .name $JSON_STRING)
+    NAME=$(jq -r .name "$JSON_STRING")
+    INTEGRATION_ID=""
 
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
+    local POLICY_JSON
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        return 1
+    fi
+
+    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
 
 }
 
@@ -148,7 +196,16 @@ elastic_fleet_integration_remove() {
 
     NAME=$2
 
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
+    local POLICY_JSON
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        return 1
+    fi
+
+    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
+    if [ -z "$INTEGRATION_ID" ]; then
+        echo "Error: Integration '$NAME' was not found in agent policy '$AGENT_POLICY'." >&2
+        return 1
+    fi
 
     JSON_STRING=$( jq -n \
                     --arg INTEGRATIONID "$INTEGRATION_ID" \

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-defend

@@ -13,7 +13,10 @@ ERROR=false
 for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/elastic-defend/*.json
 do
   printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
-  elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
+  if ! elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"; then
+    ERROR=true
+    continue
+  fi
   if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Upgrading integration policy\n"
       if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server

@@ -7,20 +7,35 @@
 . /usr/sbin/so-elastic-fleet-common
 
 # Get all the fleet policies
-json_output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -L -X GET "localhost:5601/api/fleet/agent_policies" -H 'kbn-xsrf: true')
+if ! json_output=$(fleet_api "agent_policies" -H 'kbn-xsrf: true'); then
+    echo "Error: Failed to retrieve Fleet agent policies." >&2
+    exit 1
+fi
+
+if ! jq -e '.items' <<<"$json_output" >/dev/null 2>&1; then
+    echo "Error: Invalid Fleet agent policies response." >&2
+    exit 1
+fi
 
 # Extract the IDs that start with "FleetServer_"
-POLICY=$(echo "$json_output" | jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id')
+POLICY=$(jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id' <<<"$json_output")
 
 # Iterate over each ID in the POLICY variable
 for POLICYNAME in $POLICY; do
     printf "\nUpdating Policy: $POLICYNAME\n"
 
-    # First get the Integration ID
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$POLICYNAME" | jq -r '.item.package_policies[] | select(.package.name == "fleet_server") | .id')  
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$POLICYNAME"); then
+        exit 1
+    fi
+
+    INTEGRATION_ID=$(jq -r '.item.package_policies[]? | select(.package.name == "fleet_server") | .id' <<<"$POLICY_JSON")
+    if [ -z "$INTEGRATION_ID" ]; then
+        echo "Error: fleet_server integration was not found in agent policy '$POLICYNAME'." >&2
+        exit 1
+    fi
 
     # Modify the default integration policy to update the policy_id and an with the correct naming
-	UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
+    UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
     .policy_id = $policy_id |
     .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 

salt/elasticfleet/tools/sbin_jinja/so-elastic-agent-gen-installers

@@ -22,12 +22,19 @@ NUM_RUNNING=$(pgrep -cf "/bin/bash /sbin/so-elastic-agent-gen-installers")
 
 for i in {1..30}
 do
-   ENROLLMENTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
+   ENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial")
+   TOKEN_RC=$?
+   if [ "$TOKEN_RC" -eq 2 ]; then
+     exit 1
+   fi
    FLEETHOST=$(curl -K /opt/so/conf/elasticsearch/curl.config 'http://localhost:5601/api/fleet/fleet_server_hosts/grid-default' | jq -r  '.item.host_urls[]' | paste -sd ',')
-if [[ $FLEETHOST ]] && [[  $ENROLLMENTOKEN ]]; then break; else sleep 10; fi
+   if [[ -n "$FLEETHOST" ]] && [[ -n "$ENROLLMENTOKEN" ]]; then
+     break
+   fi
+   sleep 10
 done
 
-if [[ -z $FLEETHOST ]] || [[ -z $ENROLLMENTOKEN ]]; then 
+if [[ -z "$FLEETHOST" ]] || [[ -z "$ENROLLMENTOKEN" ]]; then
   printf "\nFleet Host URL, Enrollment Token or Elastic Version empty - exiting..."
   printf "\nFleet Host: $FLEETHOST, Enrollment Token: $ENROLLMENTOKEN\n"
   exit 1
@@ -67,19 +74,25 @@ for GOOS in "${GOTARGETOS[@]}"; do
     GOARCH="amd64"
     if [[ $GOOS == 'darwin/arm64' ]]; then GOOS="darwin" && GOARCH="arm64"; fi
     printf "\n\n### Generating $GOOS/$GOARCH Installer...\n"
-    docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
+    if ! docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
     --mount type=bind,source=/etc/pki/tls/certs/,target=/workspace/files/cert/ \
     --mount type=bind,source=/nsm/elastic-agent-workspace/,target=/workspace/files/elastic-agent/ \
     --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ \
-    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}
+    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}; then
+        printf "\n### ERROR: Failed to generate $GOOS/$GOARCH installer. Exiting...\n"
+        exit 1
+    fi
     printf "\n### $GOOS/$GOARCH Installer Generated...\n"
 done
 
 printf "\n\n### Generating MSI...\n"
 cp /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64 /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64.exe
-docker run \
+if ! docker run \
 --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ -w /output \
-{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs
+{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs; then
+    printf "\n### ERROR: Failed to generate MSI. Exiting...\n"
+    exit 1
+fi
 printf "\n### MSI Generated...\n"
 
 # Verify installers were created

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-setup

@@ -202,26 +202,9 @@ fi
 ### Finalization ###
 
 # Query for Enrollment Tokens for default policies
-if ENDPOINTSENROLLMENTOKEN_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
-    ENDPOINTSENROLLMENTOKEN=$(echo "$ENDPOINTSENROLLMENTOKEN_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
-else
-    echo -e "\nFailed to query for Endpoints enrollment token"
-    exit 1
-fi
-
-if GRIDNODESENROLLMENTOKENGENERAL_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
-    GRIDNODESENROLLMENTOKENGENERAL=$(echo "$GRIDNODESENROLLMENTOKENGENERAL_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_general")) | .api_key')
-else
-    echo -e "\nFailed to query for Grid nodes - General enrollment token"
-    exit 1
-fi
-
-if GRIDNODESENROLLMENTOKENHEAVY_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
-    GRIDNODESENROLLMENTOKENHEAVY=$(echo "$GRIDNODESENROLLMENTOKENHEAVY_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_heavy")) | .api_key')
-else
-    echo -e "\nFailed to query for Grid nodes - Heavy enrollment token"
-    exit 1
-fi
+ENDPOINTSENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial") || exit 1
+GRIDNODESENROLLMENTOKENGENERAL=$(elastic_fleet_active_enrollment_token "so-grid-nodes_general") || exit 1
+GRIDNODESENROLLMENTOKENHEAVY=$(elastic_fleet_active_enrollment_token "so-grid-nodes_heavy") || exit 1
 
 # Store needed data in minion pillar
 pillar_file=/opt/so/saltstack/local/pillar/minions/{{ GLOBALS.minion_id }}.sls

salt/elasticsearch/config.sls

@@ -32,13 +32,14 @@ elasticsearch:
     - gid: 930
     - home: /opt/so/conf/elasticsearch
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticsearch_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - exclude_pat:
       - so-elasticsearch-pipelines # exclude this because we need to watch it for changes, we sync it in another state
@@ -49,8 +50,8 @@ so-elasticsearch-system-indices-patch-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-system-indices-patch
     - source: salt://elasticsearch/tools/sbin/so-elasticsearch-system-indices-patch
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - mode: 755
     - show_changes: False
 
@@ -58,8 +59,8 @@ elasticsearch_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -72,8 +73,8 @@ so-elasticsearch-ilm-policy-load-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-ilm-policy-load
     - source: salt://elasticsearch/tools/sbin_jinja/so-elasticsearch-ilm-policy-load
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - mode: 754
     - template: jinja
     - defaults:
@@ -84,8 +85,8 @@ so-elasticsearch-pipelines-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-pipelines
     - source: salt://elasticsearch/tools/sbin/so-elasticsearch-pipelines
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - mode: 754
     - show_changes: False
 

salt/elasticsearch/defaults.yaml

@@ -1160,6 +1160,7 @@ elasticsearch:
         - so-fleet_agent_id_verification-1
         - so-logs-mappings
         - so-logs-settings
+        - detections-alerts-mappings
         data_stream:
           allow_custom_routing: false
           hidden: false
@@ -3309,6 +3310,7 @@ elasticsearch:
         composed_of:
         - event-mappings
         - logs-system.security@package
+        - so-fleet_system.security_caseless-1
         - logs-system.security@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4175,6 +4177,7 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.forwarded@package
+        - so-fleet_process_caseless-1
         - logs-windows.forwarded@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4224,6 +4227,7 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.powershell@package
+        - so-fleet_process_caseless-1
         - logs-windows.powershell@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4273,6 +4277,7 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.powershell_operational@package
+        - so-fleet_process_caseless-1
         - logs-windows.powershell_operational@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4322,6 +4327,7 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.sysmon_operational@package
+        - so-fleet_process_caseless-1
         - logs-windows.sysmon_operational@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1

salt/elasticsearch/files/ingest/global@custom

@@ -99,7 +99,7 @@
         },
         {
             "set": {
-                "if": "ctx.tags != null && ctx.tags.contains('import')",
+                "if": "ctx.tags != null && ctx.tags.contains('import') && ctx._index != null && ctx._index.startsWith('logs-import-')",
                 "override": true,
                 "field": "data_stream.dataset",
                 "value": "import"
@@ -107,7 +107,7 @@
         },
         {
             "set": {
-                "if": "ctx.tags != null && ctx.tags.contains('import')",
+                "if": "ctx.tags != null && ctx.tags.contains('import') && ctx._index != null && ctx._index.startsWith('logs-import-')",
                 "override": true,
                 "field": "data_stream.namespace",
                 "value": "so"

salt/elasticsearch/files/ingest/import.evtx

@@ -0,0 +1,31 @@
+{
+  "description" : "import.evtx: normalize imported EVTX and reroute to logs-<dataset>-import",
+  "processors" : [
+    { "script":  {
+        "description": "Host from the event, not the importing node",
+        "lang": "painless",
+        "source": "Map host = ['os': ['type': 'windows', 'family': 'windows', 'platform': 'windows']]; def cn = ctx.winlog?.computer_name; if (cn != null && cn.toString().length() > 0) { String name = cn.toString(); int dot = name.indexOf('.'); if (dot > 0) { name = name.substring(0, dot); } host.put('hostname', name); host.put('name', name.toLowerCase()); } ctx.host = host;"
+    } },
+    { "script":  {
+        "description": "String event IDs, as Winlogbeat sends",
+        "lang": "painless",
+        "source": "if (ctx.winlog?.event_id != null) { ctx.winlog.event_id = ctx.winlog.event_id.toString(); } if (ctx.event?.code != null) { ctx.event.code = ctx.event.code.toString(); }"
+    } },
+    { "script":  {
+        "description": "Unnamed <Data> to param1..N, as Winlogbeat",
+        "lang": "painless",
+        "if": "ctx.winlog?.event_data?.Data instanceof Map && ctx.winlog.event_data.Data['#text'] != null",
+        "source": "def t = ctx.winlog.event_data.Data['#text']; List vals = t instanceof List ? t : [t]; for (int i = 0; i < vals.size(); i++) { ctx.winlog.event_data['param' + (i + 1)] = vals.get(i); } ctx.winlog.event_data.remove('Data');"
+    } },
+    { "script":  {
+        "description": "String values and LF line endings, as Winlogbeat",
+        "lang": "painless",
+        "if": "ctx.winlog?.event_data instanceof Map || ctx.winlog?.user_data instanceof Map",
+        "source": "String lf = String.valueOf((char) 10); String crlf = String.valueOf((char) 13) + lf; for (def key : ['event_data', 'user_data']) { def m = ctx.winlog[key]; if (!(m instanceof Map)) { continue; } for (def e : m.entrySet()) { def v = e.getValue(); if (v instanceof String) { e.setValue(v.replace(crlf, lf)); } else if (v instanceof Number || v instanceof Boolean) { e.setValue(v.toString()); } } }"
+    } },
+    { "set":     { "description": "event.kind, as Winlogbeat", "field": "event.kind", "value": "event", "override": false } },
+    { "set":     { "field": "data_stream.dataset", "copy_from": "event.dataset", "override": true, "ignore_empty_value": true } },
+    { "set":     { "field": "data_stream.namespace", "value": "import", "override": true } },
+    { "reroute": { "dataset": "{{data_stream.dataset}}", "namespace": "{{data_stream.namespace}}" } }
+  ]
+}

salt/elasticsearch/files/ingest/logs-system.auth@custom

@@ -0,0 +1,34 @@
+{
+    "version": 1,
+    "_meta": {
+        "managed_by": "securityonion",
+        "managed": true
+    },
+    "description": "Custom pipeline for the System integration's auth data stream.",
+    "processors": [
+        {
+            "trim": {
+                "description": "Grok leaves a leading space on 'invalid user' names (elastic/integrations#12174) and, before 2.23.2, sudo padding",
+                "field": "user.name",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "trim": {
+                "description": "Appended from the untrimmed user.name",
+                "field": "related.user",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "description": "Dedupe after trimming",
+                "if": "ctx.related?.user instanceof List",
+                "source": "ctx.related.user = new ArrayList(new LinkedHashSet(ctx.related.user));",
+                "ignore_failure": true
+            }
+        }
+    ]
+}

salt/elasticsearch/files/ingest/suricata.fileinfo

@@ -5,7 +5,8 @@
     { "rename": 	{ "field": "message2.proto", 			"target_field": "network.transport",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.app_proto", 		"target_field": "network.protocol",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.filename", 	"target_field": "file.name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "file.bytes.missing",	"ignore_missing": true 	} },
+    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "suricata.fileinfo.gaps",	"ignore_missing": true 	} },
+    { "set":		{ "if": "ctx.suricata?.fileinfo?.gaps == false", 	"field": "file.bytes.missing",	"value": 0 		} },
     { "rename": 	{ "field": "message2.fileinfo.magic", 		"target_field": "file.mime_type",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.md5", 		"target_field": "hash.md5",		"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.sha1", 		"target_field": "hash.sha1",		"ignore_missing": true 	} },

salt/elasticsearch/templates/component/elastic-agent/so-fleet_process_caseless-1.json

@@ -0,0 +1,123 @@
+{
+  "_meta": {
+    "managed_by": "security_onion",
+    "managed": true,
+    "description": "Adds .caseless for Lucene queries. Restates each field's package type and .text."
+  },
+  "template": {
+    "mappings": {
+      "properties": {
+        "process": {
+          "properties": {
+            "executable": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                },
+                "text": {
+                  "type": "match_only_text"
+                }
+              }
+            },
+            "name": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                },
+                "text": {
+                  "type": "match_only_text"
+                }
+              }
+            },
+            "command_line": {
+              "type": "wildcard",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                },
+                "text": {
+                  "type": "match_only_text"
+                }
+              }
+            },
+            "parent": {
+              "properties": {
+                "executable": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    },
+                    "text": {
+                      "type": "match_only_text"
+                    }
+                  }
+                },
+                "name": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    },
+                    "text": {
+                      "type": "match_only_text"
+                    }
+                  }
+                },
+                "command_line": {
+                  "type": "wildcard",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    },
+                    "text": {
+                      "type": "match_only_text"
+                    }
+                  }
+                }
+              }
+            }
+          }
+        },
+        "file": {
+          "properties": {
+            "path": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                },
+                "text": {
+                  "type": "match_only_text"
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}

salt/elasticsearch/templates/component/elastic-agent/so-fleet_system.security_caseless-1.json

@@ -0,0 +1,80 @@
+{
+  "_meta": {
+    "managed_by": "security_onion",
+    "managed": true,
+    "description": "Adds .caseless for Lucene queries. Keeps each field's existing keyword type."
+  },
+  "template": {
+    "mappings": {
+      "properties": {
+        "process": {
+          "properties": {
+            "command_line": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                }
+              }
+            },
+            "parent": {
+              "properties": {
+                "executable": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    }
+                  }
+                },
+                "name": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    }
+                  }
+                },
+                "command_line": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    }
+                  }
+                }
+              }
+            }
+          }
+        },
+        "file": {
+          "properties": {
+            "path": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}

salt/elasticsearch/templates/component/so/detection-mappings.json

@@ -50,6 +50,18 @@
               "ignore_above": 1024,
               "type": "keyword"
             },
+            "ruleType": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "correlationType": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "correlationTimespan": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
             "content": {
               "type": "text"
             },

salt/elasticsearch/templates/component/so/detections-alerts-mappings.json

@@ -0,0 +1,149 @@
+{
+  "template": {
+    "mappings": {
+      "properties": {
+        "tags": {
+          "ignore_above": 1024,
+          "type": "keyword"
+        },
+        "sigma_level": {
+          "ignore_above": 1024,
+          "type": "keyword"
+        },
+        "rule": {
+          "properties": {
+            "name": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "uuid": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "category": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "product": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "service": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "correlation": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            }
+          }
+        },
+        "event": {
+          "properties": {
+            "severity": {
+              "type": "long"
+            },
+            "severity_label": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "module": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "dataset": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "kind": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "reason": {
+              "type": "match_only_text",
+              "fields": {
+                "keyword": {
+                  "ignore_above": 1024,
+                  "type": "keyword"
+                }
+              }
+            },
+            "original": {
+              "type": "keyword",
+              "index": false,
+              "doc_values": false
+            }
+          }
+        },
+        "event_data": {
+          "properties": {
+            "@timestamp": {
+              "type": "date"
+            },
+            "window_start": {
+              "type": "date"
+            },
+            "event_count": {
+              "type": "long"
+            },
+            "value_count": {
+              "type": "long"
+            },
+            "event_type_count": {
+              "type": "long"
+            },
+            "value_sum": {
+              "type": "double"
+            },
+            "value_avg": {
+              "type": "double"
+            },
+            "value_percentile": {
+              "type": "double"
+            },
+            "value_median": {
+              "type": "double"
+            }
+          }
+        },
+        "labels": {
+          "properties": {
+            "correlation_group_by": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "correlation_group": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            }
+          }
+        },
+        "related": {
+          "properties": {
+            "ip": {
+              "type": "ip"
+            },
+            "user": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "hosts": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            }
+          }
+        },
+        "error": {
+          "properties": {
+            "message": {
+              "type": "match_only_text"
+            }
+          }
+        }
+      }
+    }
+  },
+  "_meta": {
+    "description": "Fields written by the ElastAlert SecurityOnionESAlerter to logs-detections.alerts-so"
+  }
+}

salt/firewall/iptables.jinja

@@ -4,11 +4,19 @@
 {%- set role = GLOBALS.role.split('-')[1] %}
 {%- from 'firewall/containers.map.jinja' import NODE_CONTAINERS %}
 
+{%- set NODE_NETWORKS = [] %}
+{%- for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{%-   if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+{%-     do NODE_NETWORKS.append(NETNAME) %}
+{%-   endif %}
+{%- endfor %}
+
 {%- set PR = [] %}
 {%- set D1 = [] %}
 {%- set D2 = [] %}
 {%- for container in NODE_CONTAINERS %}
 {%-   set IP = DOCKERMERGED.containers[container].ip %}
+{%-   set BRIDGE = DOCKERMERGED.containers[container].network %}
 {%-   if DOCKERMERGED.containers[container].port_bindings is defined %}
 {%-     for binding in DOCKERMERGED.containers[container].port_bindings %}
 {#-       cant split int so we convert to string #}
@@ -35,11 +43,11 @@
 {%-         endif %}
 {%-         do PR.append("-A POSTROUTING -s " ~ DOCKERMERGED.containers[container].ip ~ "/32 -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 -p " ~  proto ~ " -m " ~ proto  ~ " --dport " ~ containerPort ~ " -j MASQUERADE") %}
 {%-         if bindip | length and bindip != '0.0.0.0' %}
-{%-           do D1.append("-A DOCKER -d " ~ bindip ~ "/32 ! -i sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
+{%-           do D1.append("-A DOCKER -d " ~ bindip ~ "/32 ! -i " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
 {%-         else %}
-{%-           do D1.append("-A DOCKER ! -i sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
+{%-           do D1.append("-A DOCKER ! -i " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
 {%-         endif %}
-{%-         do D2.append("-A DOCKER -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 ! -i sobridge -o sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ containerPort ~ " -j ACCEPT") %}
+{%-         do D2.append("-A DOCKER -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 ! -i " ~ BRIDGE ~ " -o " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ containerPort ~ " -j ACCEPT") %}
 {%-     endfor %}
 {%-   endif %}
 {%- endfor %}
@@ -52,11 +60,15 @@
 :DOCKER - [0:0]
 -A PREROUTING -m addrtype --dst-type LOCAL -j DOCKER
 -A OUTPUT ! -d 127.0.0.0/8 -m addrtype --dst-type LOCAL -j DOCKER
--A POSTROUTING -s {{DOCKERMERGED.range}} ! -o sobridge -j MASQUERADE
+{%- for NETNAME in NODE_NETWORKS %}
+-A POSTROUTING -s {{ DOCKERMERGED.networks[NETNAME].range }} ! -o {{ NETNAME }} -j MASQUERADE
+{%- endfor %}
 {%- for rule in PR %}
 {{ rule }}
 {%- endfor %}
--A DOCKER -i sobridge -j RETURN
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER -i {{ NETNAME }} -j RETURN
+{%- endfor %}
 {%- for rule in D1 %}
 {{ rule }}
 {%- endfor %}
@@ -97,10 +109,12 @@ COMMIT
 {%- endif %}
 -A FORWARD -j DOCKER-USER
 -A FORWARD -j DOCKER-ISOLATION-STAGE-1
--A FORWARD -o sobridge -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A FORWARD -o sobridge -j DOCKER
--A FORWARD -i sobridge ! -o sobridge -j ACCEPT
--A FORWARD -i sobridge -o sobridge -j ACCEPT
+{%- for NETNAME in NODE_NETWORKS %}
+-A FORWARD -o {{ NETNAME }} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
+-A FORWARD -o {{ NETNAME }} -j DOCKER
+-A FORWARD -i {{ NETNAME }} ! -o {{ NETNAME }} -j ACCEPT
+-A FORWARD -i {{ NETNAME }} -o {{ NETNAME }} -j ACCEPT
+{%- endfor %}
 -A FORWARD -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
 -A FORWARD -i lo -j ACCEPT
 -A FORWARD -m conntrack --ctstate INVALID -j DROP
@@ -112,13 +126,18 @@ COMMIT
 {%- for rule in D2 %}
 {{ rule }}
 {%- endfor %}
-
--A DOCKER-ISOLATION-STAGE-1 -i sobridge ! -o sobridge -j DOCKER-ISOLATION-STAGE-2
+{% for NETNAME in NODE_NETWORKS %}
+-A DOCKER-ISOLATION-STAGE-1 -i {{ NETNAME }} ! -o {{ NETNAME }} -j DOCKER-ISOLATION-STAGE-2
+{%- endfor %}
 -A DOCKER-ISOLATION-STAGE-1 -j RETURN
--A DOCKER-ISOLATION-STAGE-2 -o sobridge -j DROP
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER-ISOLATION-STAGE-2 -o {{ NETNAME }} -j DROP
+{%- endfor %}
 -A DOCKER-ISOLATION-STAGE-2 -j RETURN
--A DOCKER-USER ! -i sobridge -o sobridge -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-USER ! -i sobridge -o sobridge -j LOGGING
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER-USER ! -i {{ NETNAME }} -o {{ NETNAME }} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
+-A DOCKER-USER ! -i {{ NETNAME }} -o {{ NETNAME }} -j LOGGING
+{%- endfor %}
 -A DOCKER-USER -j RETURN
 -A LOGGING -m limit --limit 2/min -j LOG --log-prefix "IPTables-dropped: "
 -A LOGGING -j DROP

salt/firewall/map.jinja

@@ -4,8 +4,12 @@
 
 {# add our ip to self #}
 {% do FIREWALL_DEFAULT.firewall.hostgroups.self.append(GLOBALS.node_ip) %}
-{# add dockernet range #}
-{% do FIREWALL_DEFAULT.firewall.hostgroups.dockernet.append(DOCKERMERGED.range) %}
+{# add dockernet ranges #}
+{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{%   if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+{%     do FIREWALL_DEFAULT.firewall.hostgroups.dockernet.append(NETWORK.range) %}
+{%   endif %}
+{% endfor %}
 
 {% if GLOBALS.role == 'so-idh' %}
 {%   from 'idh/opencanary_config.map.jinja' import IDH_PORTGROUPS %}

salt/hydra/enabled.sls

@@ -26,8 +26,8 @@ so-hydra:
     - hostname: hydra
     - name: so-hydra
     - networks:
-      - sobridge:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-hydra'].ip }}
+      - soauth:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-hydra'].ips['soauth'] }}
     - binds:
       - /opt/so/conf/hydra/:/hydra-conf:ro
       - /opt/so/log/hydra/:/hydra-log:rw
@@ -73,7 +73,7 @@ delete_so-hydra_so-status.disabled:
 
 wait_for_hydra:
   http.wait_for_successful_query:
-    - name: 'http://{{ GLOBALS.manager }}:4444/health/alive'
+    - name: 'http://{{ DOCKERMERGED.containers['so-hydra'].ips['soauth'] }}:4444/health/alive'
     - ssl: True
     - verify_ssl: False
     - status:

salt/hypervisor/init.sls

@@ -21,12 +21,16 @@ hypervisor_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://hypervisor/tools/sbin
+    - user: root
+    - group: root
     - file_mode: 744
 
 hypervisor_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://hypervisor/tools/sbin_jinja
+    - user: root
+    - group: root
     - template: jinja
     - file_mode: 744
 

salt/idh/config.sls

@@ -86,8 +86,8 @@ idh_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://idh/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #idh_sbin_jinja:

salt/influxdb/config.sls

@@ -41,8 +41,8 @@ influxdb_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://influxdb/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #influxdb_sbin_jinja:

salt/influxdb/enabled.sls

@@ -94,9 +94,11 @@ metrics_link_file:
       - docker_container: so-influxdb
 
 # Install cron job to determine size of influxdb for telegraf
+# telegraf reads this while the cron rewrites it, so write aside and rename rather than
+# truncating in place. tgraflogdir recurses ownership, so the temp file is chowned to match
 get_influxdb_size:
   cron.present:
-    - name: 'du -s -k /nsm/influxdb | cut -f1 > /opt/so/log/telegraf/influxdb_size.log 2>&1'
+    - name: 'du -s -k /nsm/influxdb | cut -f1 > /opt/so/log/telegraf/influxdb_size.log.tmp 2>&1; chown 939:939 /opt/so/log/telegraf/influxdb_size.log.tmp; mv -f /opt/so/log/telegraf/influxdb_size.log.tmp /opt/so/log/telegraf/influxdb_size.log'
     - identifier: get_influxdb_size
     - user: root
     - minute: '*/1'

salt/kafka/config.sls

@@ -21,6 +21,7 @@ kafka_user:
     - gid: 960
     - home: /opt/so/conf/kafka
     - createhome: False
+    - shell: /sbin/nologin
 
 kafka_home_dir:
   file.absent:
@@ -30,16 +31,16 @@ kafka_sbin_tools:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kafka/tools/sbin
-    - user: 960
-    - group: 960
+    - user: root
+    - group: root
     - file_mode: 755
 
 kafka_sbin_jinja_tools:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kafka/tools/sbin_jinja
-    - user: 960
-    - group: 960
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - defaults:

salt/kibana/config.sls

@@ -22,6 +22,7 @@ kibana:
     - gid: 932
     - home: /opt/so/conf/kibana
     - createhome: False
+    - shell: /sbin/nologin
 
 # Drop the correct nginx config based on role
 
@@ -36,16 +37,16 @@ kibana_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kibana/tools/sbin
-    - user: 932
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 kibana_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kibana/tools/sbin_jinja
-    - user: 932
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - defaults:

salt/kratos/config.sls

@@ -27,6 +27,7 @@ kratos:
     - uid: 928
     - gid: 928
     - home: /opt/so/conf/kratos
+    - shell: /sbin/nologin
 
 kratosdir:
   file.directory:

salt/kratos/enabled.sls

@@ -19,8 +19,8 @@ so-kratos:
     - hostname: kratos
     - name: so-kratos
     - networks:
-      - sobridge:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-kratos'].ip }}
+      - soauth:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-kratos'].ips['soauth'] }}
     - binds:
       - /opt/so/conf/kratos/:/kratos-conf:ro
       - /opt/so/log/kratos/:/kratos-log:rw
@@ -71,7 +71,7 @@ delete_so-kratos_so-status.disabled:
 
 wait_for_kratos:
   http.wait_for_successful_query:
-    - name: 'http://{{ GLOBALS.manager }}:4434/'
+    - name: 'http://{{ DOCKERMERGED.containers['so-kratos'].ips['soauth'] }}:4434/'
     - ssl: True
     - verify_ssl: False
     - status:

salt/libvirt/64962/init.sls

@@ -6,6 +6,8 @@ so-fix-salt-ldap_script:
   file.managed:
     - name: /usr/sbin/so-fix-salt-ldap.py
     - source: salt://libvirt/64962/scripts/so-fix-salt-ldap.py
+    - user: root
+    - group: root
     - mode: 744
 
 fix-salt-ldap:

salt/logstash/config.sls

@@ -35,13 +35,14 @@ logstash:
     - uid: 931
     - gid: 931
     - home: /opt/so/conf/logstash
+    - shell: /sbin/nologin
 
 logstash_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://logstash/tools/sbin
-    - user: 931
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #logstash_sbin_jinja:

salt/manager/init.sls

@@ -113,8 +113,8 @@ manager_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://manager/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - exclude_pat:
       - "*_test.py"
@@ -124,8 +124,8 @@ manager_sbin_jinja:
   file.recurse:
     - name: /usr/sbin/
     - source: salt://manager/tools/sbin_jinja/
-    - user: socore
-    - group: socore
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -166,7 +166,7 @@ so-repo-sync:
 
 so_fleetagent_status:
   cron.present:
-    - name: /usr/sbin/so-elasticagent-status > /opt/so/log/agents/agentstatus.log 2>&1
+    - name: '/usr/sbin/so-elasticagent-status > /opt/so/log/agents/agentstatus.log.tmp 2>&1; mv -f /opt/so/log/agents/agentstatus.log.tmp /opt/so/log/agents/agentstatus.log'
     - identifier: so_fleetagent_status
     - user: root
     - minute: '*/5'
@@ -190,11 +190,15 @@ so_fleetagent_monitor:
   - month: '*'
   - dayweek: '*'
 
-socore_own_saltstack_default:
+# This tree is the source of every root-executed script (/usr/sbin, reactors, _runners,
+# engines, salt-relay.sh). SOC mounts /opt/so/saltstack rw as uid 939 but only writes
+# under local/. Do not add dir_mode/file_mode here -- SOC reads default/ and 750/640
+# would break its config load.
+root_own_saltstack_default:
   file.directory:
     - name: /opt/so/saltstack/default
-    - user: socore
-    - group: socore
+    - user: root
+    - group: root
     - recurse:
       - user
       - group

salt/manager/tools/sbin/so-client

@@ -106,7 +106,8 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-hydraUrl=${HYDRA_URL:-http://127.0.0.1:4445}
+hydraContainer=${HYDRA_CONTAINER:-so-hydra}
+hydraUrl=${HYDRA_URL:-http://localhost:4445}
 socRolesFile=${SOC_ROLES_FILE:-/opt/so/conf/soc/soc_clients_roles}
 soUID=${SOCORE_UID:-939}
 soGID=${SOCORE_GID:-939}
@@ -124,6 +125,10 @@ function fail() {
   exit 1
 }
 
+function hydraCurl() {
+  docker exec "$hydraContainer" curl "$@"
+}
+
 function require() {
   cmd=$1
   which "$1" 2>&1 > /dev/null
@@ -133,8 +138,8 @@ function require() {
 # Verify this environment is capable of running this script
 function verifyEnvironment() {
   require "jq"
-  require "curl"
-  response=$(curl -Ss -L ${hydraUrl}/health/alive)
+  require "docker"
+  response=$(hydraCurl -Ss -L ${hydraUrl}/health/alive)
   [[ "$response" != '{"status":"ok"}' ]] && fail "Unable to communicate with Hydra; specify URL via HYDRA_URL environment variable"
 }
 
@@ -164,7 +169,7 @@ function ensureRoleFileExists() {
 }
 
 function listClients() {
-  response=$(curl -Ss -L -f ${hydraUrl}/admin/clients)
+  response=$(hydraCurl -Ss -L -f ${hydraUrl}/admin/clients)
   [[ $? != 0 ]] && fail "Unable to communicate with Hydra"
 
   clientIds=$(echo "${response}" | jq -r ".[] | .client_id" | sort)
@@ -251,7 +256,7 @@ function createClient() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X POST ${hydraUrl}/admin/clients -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X POST ${hydraUrl}/admin/clients -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -283,7 +288,7 @@ function update() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -305,7 +310,7 @@ function generateSecret() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -317,7 +322,7 @@ function deleteClient() {
 
   [[ ${identityId} == "" ]] && fail "Client not found"
 
-  response=$(curl -Ss -XDELETE -L --fail-with-body "${hydraUrl}/admin/clients/$identityId")
+  response=$(hydraCurl -Ss -XDELETE -L --fail-with-body "${hydraUrl}/admin/clients/$identityId")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"

salt/manager/tools/sbin/so-saltstack-update

@@ -124,8 +124,8 @@ copy_new_files() {
   
   rsync -a salt $default_salt_dir/
   rsync -a pillar $default_salt_dir/
-  chown -R socore:socore $default_salt_dir/salt
-  chown -R socore:socore $default_salt_dir/pillar
+  chown -R root:root $default_salt_dir/salt
+  chown -R root:root $default_salt_dir/pillar
   chmod 755 $default_salt_dir/pillar/firewall/addfirewall.sh
 
   rm -rf /tmp/sogh

salt/manager/tools/sbin/so-user

@@ -129,7 +129,8 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-kratosUrl=${KRATOS_URL:-http://127.0.0.1:4434/admin}
+kratosContainer=${KRATOS_CONTAINER:-so-kratos}
+kratosUrl=${KRATOS_URL:-http://localhost:4434/admin}
 databasePath=${KRATOS_DB_PATH:-/nsm/kratos/db/db.sqlite}
 databaseTimeout=${KRATOS_DB_TIMEOUT:-5000}
 bcryptRounds=${BCRYPT_ROUNDS:-12}
@@ -154,6 +155,10 @@ function fail() {
   exit 1
 }
 
+function kratosCurl() {
+  docker exec "$kratosContainer" curl "$@"
+}
+
 function require() {
   cmd=$1
   which "$1" 2>&1 > /dev/null
@@ -164,18 +169,18 @@ function require() {
 function verifyEnvironment() {
   require "htpasswd"
   require "jq"
-  require "curl"
+  require "docker"
   require "openssl"
   require "sqlite3"
   [[ ! -f $databasePath ]] && fail "Unable to find database file; specify path via KRATOS_DB_PATH environment variable"
-  response=$(curl -Ss -L ${kratosUrl}/)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/)
   [[ "$response" != "404 page not found" ]] && fail "Unable to communicate with Kratos; specify URL via KRATOS_URL environment variable"
 }
 
 function findIdByEmail() {
   email=${1,,}
 
-  response=$(curl -Ss -L ${kratosUrl}/identities)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities)
   identityId=$(echo "${response}" | jq -r ".[] | select(.verifiable_addresses[0].value == \"$email\") | .id")
   echo $identityId
 }
@@ -416,7 +421,7 @@ function syncAll() {
 }
 
 function listUsers() {
-  response=$(curl -Ss -L ${kratosUrl}/identities)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities)
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   users=$(echo "${response}" | jq -r ".[] | .verifiable_addresses[0].value" | sort)
@@ -495,7 +500,7 @@ function createUser() {
 EOF
   )
   
-  response=$(curl -Ss -L ${kratosUrl}/identities -d "$addUserJson")
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities -d "$addUserJson")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   identityId=$(echo "${response}" | jq -r ".id")
@@ -518,7 +523,7 @@ function updateStatus() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   schemaId=$(echo "$response" | jq -r .schema_id)
@@ -531,7 +536,7 @@ function updateStatus() {
     state="inactive"
   fi
   body="{ \"schema_id\": \"$schemaId\", \"state\": \"$state\", \"traits\": $traitBlock }"
-  response=$(curl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
+  response=$(kratosCurl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
   [[ $? != 0 ]] && fail "Unable to update user"
 }
 
@@ -550,7 +555,7 @@ function updateUserProfile() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   schemaId=$(echo "$response" | jq -r .schema_id)
@@ -559,7 +564,7 @@ function updateUserProfile() {
   traitBlock="{\"email\":\"$email\",\"firstName\":\"$firstName\",\"lastName\":\"$lastName\",\"note\":\"$note\"}"
 
   body="{ \"schema_id\": \"$schemaId\", \"state\": \"$state\", \"traits\": $traitBlock }"
-  response=$(curl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
+  response=$(kratosCurl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
   [[ $? != 0 ]] && fail "Unable to update user"
 }
 
@@ -569,7 +574,7 @@ function deleteUser() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -XDELETE -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -XDELETE -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   rolesTmpFile="${socRolesFile}.tmp"

salt/manager/tools/sbin/so-yaml.py

@@ -42,7 +42,8 @@ def loadYaml(filename):
     try:
         with open(filename, "r") as file:
             content = file.read()
-            return yaml.safe_load(content)
+            loaded = yaml.safe_load(content)
+            return loaded if loaded is not None else {}
     except FileNotFoundError:
         print(f"File not found: {filename}", file=sys.stderr)
         sys.exit(1)

salt/manager/tools/sbin/so-yaml_test.py

@@ -95,6 +95,20 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep2: ab\nkey2: false\n"
         self.assertEqual(actual, expected)
 
+    def test_remove_empty_file(self):
+        filename = "/tmp/so-yaml_test-remove-empty.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        code = soyaml.remove([filename, "key1"])
+        self.assertEqual(code, 0)
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        self.assertEqual(actual, "{}\n")
+
     def test_remove_missing_args(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -294,6 +308,36 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep1: 45\n    deep2: d\nkey2: false\nkey3:\n- e\n- f\n- g\n"
         self.assertEqual(actual, expected)
 
+    def test_add_empty_file(self):
+        filename = "/tmp/so-yaml_test-add-empty.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        code = soyaml.add([filename, "telegraf.output", "BOTH"])
+        self.assertEqual(code, 0)
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "telegraf:\n  output: BOTH\n"
+        self.assertEqual(actual, expected)
+
+    def test_add_empty_file_simple(self):
+        filename = "/tmp/so-yaml_test-add-empty-simple.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        code = soyaml.add([filename, "telegraf", "BOTH"])
+        self.assertEqual(code, 0)
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "telegraf: BOTH\n"
+        self.assertEqual(actual, expected)
+
     def test_replace_missing_arg(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -346,6 +390,21 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep1: 46\nkey2: false\nkey3:\n- e\n- f\n- g\n"
         self.assertEqual(actual, expected)
 
+    def test_replace_empty_file(self):
+        filename = "/tmp/so-yaml_test-replace-empty.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        code = soyaml.replace([filename, "telegraf.output", "BOTH"])
+        self.assertEqual(code, 0)
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "telegraf:\n  output: BOTH\n"
+        self.assertEqual(actual, expected)
+
     def test_convert(self):
         self.assertEqual(soyaml.convertType("foo"), "foo")
         self.assertEqual(soyaml.convertType("foo.bar"), "foo.bar")
@@ -506,6 +565,18 @@ class TestRemove(unittest.TestCase):
             self.assertEqual(result, 2)
             self.assertEqual("", mock_stdout.getvalue())
 
+    def test_get_empty_file(self):
+        with patch('sys.stdout', new=StringIO()) as mock_stdout:
+            with patch('sys.stderr', new=StringIO()) as mock_stderr:
+                filename = "/tmp/so-yaml_test-get-empty.yaml"
+                file = open(filename, "w")
+                file.close()
+
+                result = soyaml.get([filename, "telegraf.output"])
+                self.assertEqual(result, 2)
+                self.assertEqual("", mock_stdout.getvalue())
+                self.assertIn("Key 'telegraf.output' not found by so-yaml.py", mock_stderr.getvalue())
+
     def test_get_usage(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -991,3 +1062,29 @@ class TestLoadYaml(unittest.TestCase):
                     soyaml.loadYaml("/tmp/so-yaml_test-unreadable.yaml")
                     sysmock.assert_called_with(1)
                     self.assertIn("Error reading file", mock_stderr.getvalue())
+
+    def test_load_yaml_empty_file(self):
+        filename = "/tmp/so-yaml_test-load-empty.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        result = soyaml.loadYaml(filename)
+        self.assertEqual(result, {})
+
+    def test_load_yaml_whitespace_only(self):
+        filename = "/tmp/so-yaml_test-load-whitespace.yaml"
+        file = open(filename, "w")
+        file.write("   \n\n  \n")
+        file.close()
+
+        result = soyaml.loadYaml(filename)
+        self.assertEqual(result, {})
+
+    def test_load_yaml_comments_only(self):
+        filename = "/tmp/so-yaml_test-load-comments.yaml"
+        file = open(filename, "w")
+        file.write("# Just a comment\n# Another comment\n")
+        file.close()
+
+        result = soyaml.loadYaml(filename)
+        self.assertEqual(result, {})

salt/manager/tools/sbin/soup

@@ -28,6 +28,7 @@ INSTALLEDSALTVERSION=$(salt --versions-report | grep Salt: | awk '{print $2}')
 # percentage like "25%"). Empty means so-soup-grid-highstate uses the salt:auto_apply:batch
 # pillar default.
 BATCHSIZE=
+DEFAULT_DOCKER_RANGE='172.17.1.0/24'
 SOUP_LOG=/root/soup.log
 SOUP_DEBUG_LOG=/root/soup-debug.log
 WHATWOULDYOUSAYYAHDOHERE=soup
@@ -605,6 +606,7 @@ preupgrade_changes() {
     [[ "$INSTALLEDVERSION" == "3.0.0" ]] && up_to_3.1.0
     [[ "$INSTALLEDVERSION" == "3.1.0" ]] && up_to_3.2.0
     [[ "$INSTALLEDVERSION" == "3.2.0" ]] && up_to_3.3.0
+    [[ "$INSTALLEDVERSION" == "3.3.0" ]] && up_to_3.4.0
     true
 }
 
@@ -623,6 +625,7 @@ postupgrade_changes() {
     [[ "$POSTVERSION" == "3.0.0" ]] && post_to_3.1.0
     [[ "$POSTVERSION" == "3.1.0" ]] && post_to_3.2.0
     [[ "$POSTVERSION" == "3.2.0" ]] && post_to_3.3.0
+    [[ "$POSTVERSION" == "3.3.0" ]] && post_to_3.4.0
     # All applicable post-upgrade steps completed; clear the resume marker.
     rm -f "$POSTVERSION_FILE"
     true
@@ -1173,6 +1176,98 @@ post_to_3.3.0() {
 }
 ### 3.3.0 End ###
 
+### 3.4.0 Scripts ###
+up_to_3.4.0() {
+  set_soauth_range
+
+  echo "Removing so-kratos, so-hydra and so-soc so they are recreated on the soauth network."
+  docker rm -f so-kratos so-hydra so-soc >> $SOUP_LOG 2>&1
+
+  # Extract the Sigma rule type for existing detections (Single vs. Correlation)
+  mkdir -p /opt/so/conf/soc/migrations
+  echo "0" > /opt/so/conf/soc/migrations/elastalert-migration-3.4.0
+  chown -R socore:socore /opt/so/conf/soc/migrations
+
+  for template in so-metrics-logstash.node so-metrics-logstash.stack_monitoring.node; do
+    if ! remove_elasticsearch_index_template "$template" "logstash node and node_cel index patterns reversed"; then
+      FINAL_MESSAGE_QUEUE+=("WARNING: Unable to automatically remove the $template index template. Addon integration templates may fail to load until it is removed:")
+      FINAL_MESSAGE_QUEUE+=("    - sudo so-elasticsearch-query _index_template/$template -XDELETE && so-checkin")
+    fi
+  done
+
+  INSTALLEDVERSION=3.4.0
+}
+
+set_soauth_range() {
+  local pillar_file=/opt/so/saltstack/local/pillar/docker/soc_docker.sls
+  local current_range suggested authnet authgw input
+
+  [[ -f "$pillar_file" ]] || return 0
+
+  current_range=$(so-yaml.py get -r "$pillar_file" docker.range 2>/dev/null) || return 0
+
+  # A default range gets the 172.17.2.0/24 from docker/defaults.yaml, same as a fresh
+  # install, so there is nothing to ask about.
+  [[ -n "$current_range" && "$current_range" != "$DEFAULT_DOCKER_RANGE" ]] || return 0
+
+  if so-yaml.py get -r "$pillar_file" docker.networks.soauth.range >/dev/null 2>&1; then
+    return 0
+  fi
+
+  suggested=$(echo "${current_range%%/*}" | awk -F'.' '{ printf "%s.%s.%s.%s", $1, $2, ($3 + 1) % 256, $4 }')
+
+  if [[ -z $UNATTENDED ]]; then
+    echo ""
+    echo "This grid uses a custom Docker range ($current_range). The authentication"
+    echo "services are moving to their own isolated network, which needs a second /24"
+    echo "that does not overlap it."
+    echo ""
+    while :; do
+      read -rp "Enter the network without the /24 suffix, or press Enter for ${suggested}: " input
+      [[ -z "$input" ]] && input="$suggested"
+      if valid_soauth_range "$input" "$current_range"; then
+        authnet="$input"
+        break
+      fi
+      echo "That range must be a valid IPv4 network, must not be within 172.17.0.0/24, and must not overlap ${current_range}."
+    done
+  else
+    if ! valid_soauth_range "$suggested" "$current_range"; then
+      FINAL_MESSAGE_QUEUE+=("WARNING: Unable to pick a range for the authentication network alongside $current_range. Set it manually before the next highstate:")
+      FINAL_MESSAGE_QUEUE+=("    - so-yaml.py add $pillar_file docker.networks.soauth.range <network>/24")
+      FINAL_MESSAGE_QUEUE+=("    - so-yaml.py add $pillar_file docker.networks.soauth.gateway <gateway>")
+      return 0
+    fi
+    authnet="$suggested"
+    FINAL_MESSAGE_QUEUE+=("NOTE: The authentication services moved to an isolated Docker network and were assigned ${authnet}/24.")
+    FINAL_MESSAGE_QUEUE+=("    - If that conflicts with your environment, update docker.networks.soauth in $pillar_file and run so-checkin.")
+  fi
+
+  authgw=$(echo "$authnet" | awk -F'.' '{print $1,$2,$3,1}' OFS='.')
+
+  echo "Assigning the authentication network the range ${authnet}/24."
+  so-yaml.py add "$pillar_file" docker.networks.soauth.range "${authnet}/24" >> $SOUP_LOG 2>&1
+  so-yaml.py add "$pillar_file" docker.networks.soauth.gateway "$authgw" >> $SOUP_LOG 2>&1
+}
+
+valid_soauth_range() {
+  local candidate=$1 docker_range=$2
+
+  valid_ip4 "$candidate" || return 1
+  [[ $candidate =~ ^172\.17\.0\. ]] && return 1
+  [[ "${candidate}/24" == "$docker_range" ]] && return 1
+  return 0
+}
+
+post_to_3.4.0() {
+  for idx in "metrics-logstash.node-default" "metrics-logstash.stack_monitoring.node-default"; do
+    rollover_index "$idx"
+  done
+
+  set_postversion 3.4.0
+}
+### 3.4.0 End ###
+
 
 repo_sync() {
   echo "Sync the local repo."

salt/nginx/config.sls

@@ -57,8 +57,8 @@ nginx_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://nginx/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #nginx_sbin_jinja:

salt/redis/config.sls

@@ -50,16 +50,16 @@ redis_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://redis/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 redis_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://redis/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
 

salt/repo/client/map.jinja

@@ -9,7 +9,7 @@
        'epel-testing.repo',
        'saltstack.repo',
        'salt-latest.repo',
-       'wazuh.repo'
+       'wazuh.repo',
        'Rocky-Base.repo',
        'Rocky-CR.repo',
        'Rocky-Debuginfo.repo',

salt/salt/init.sls

@@ -3,6 +3,8 @@ salt_bootstrap:
   file.managed:
     - name: /usr/sbin/bootstrap-salt.sh
     - source: salt://salt/scripts/bootstrap-salt.sh
+    - user: root
+    - group: root
     - mode: 755
     - show_changes: False
 
@@ -10,6 +12,6 @@ salt_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://salt/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755

salt/sensor/init.sls

@@ -35,6 +35,8 @@ combine_bond_script:
   file.managed:
     - name: /usr/sbin/so-combine-bond
     - source: salt://sensor/tools/sbin_jinja/so-combine-bond
+    - user: root
+    - group: root
     - mode: 755
     - template: jinja
     - defaults:

salt/sensoroni/config.sls

@@ -64,8 +64,8 @@ sensoroni_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://sensoroni/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #sensoroni_sbin_jinja:

salt/sensoroni/files/analyzers/whoislookup/requirements.txt

@@ -1,2 +1,3 @@
-requests>=2.31.0
-whoisit>=2.7.0
+requests>=2.34.0
+whoisit>=4.0.5
+anyio>=4.15.1

salt/soc/config.sls

@@ -120,19 +120,30 @@ crondetectionsbackup:
 
 socsigmafinalpipeline:
   file.managed:
-    - name: /opt/so/conf/soc/sigma_final_pipeline.yaml
+    - name: /opt/so/conf/soc/sigma_pipelines/sigma_final_pipeline.yml
     - source: salt://soc/files/soc/sigma_final_pipeline.yaml
     - user: 939
     - group: 939
     - mode: 600
+    - makedirs: True
 
-socsigmasopipeline:
-  file.managed:
-    - name: /opt/so/conf/soc/sigma_so_pipeline.yaml
-    - source: salt://soc/files/soc/sigma_so_pipeline.yaml
+# sigma-cli loads every *.yml here; clean removes anything else
+socsigmapipelines:
+  file.recurse:
+    - name: /opt/so/conf/soc/sigma_pipelines
+    - source: salt://soc/files/soc/sigma_pipelines
     - user: 939
     - group: 939
-    - mode: 600
+    - file_mode: 600
+    - clean: True
+    - require:
+      - file: socsigmafinalpipeline
+
+socsigmapipelinesold:
+  file.absent:
+    - names:
+      - /opt/so/conf/soc/sigma_final_pipeline.yaml
+      - /opt/so/conf/soc/sigma_so_pipeline.yaml
 
 socsigmaplaybookpipeline:
   file.managed:
@@ -171,8 +182,8 @@ soc_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://soc/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #soc_sbin_jinja:

salt/soc/defaults.map.jinja

@@ -14,6 +14,8 @@
 {%   do SOCDEFAULTS.soc.config.server.modules[module].update({'hostUrl': application_url}) %}
 {% endfor %}
 
+{% do SOCDEFAULTS.soc.config.server.modules.kratos.update({'publicHostUrl': 'http://' ~ DOCKERMERGED.containers['so-kratos'].ips['soauth'] ~ ':4433/'}) %}
+
 {# add all grid heavy nodes to soc.server.modules.elastic.remoteHostUrls #}
 {% for node_type, minions in salt['pillar.get']('elasticsearch:nodes', {}).items() %}
 {%   if node_type in ['heavynode'] %}

salt/soc/defaults.yaml

@@ -1380,6 +1380,7 @@ soc:
           retryFailureMaxAttempts: 5
         kratos:
           hostUrl:
+          publicHostUrl:
         hydra:
           hostUrl:
         elastalertengine:
@@ -1465,6 +1466,9 @@ soc:
             - core
             - emerging_threats_addon
           useEsql: false
+          esqlCaseInsensitive: true
+          esqlQueryDelaySeconds: 30
+          esqlCorrelationAllowanceSeconds: 600
         elastic:
           hostUrl:
           remoteHostUrls: []
@@ -1492,6 +1496,9 @@ soc:
           org: Security Onion
           bucket: telegraf/so_short_term
           verifyCert: false
+        notification:
+          dismissedPruneDays: 30
+          enabled: true
         playbook:
           autoUpdateEnabled: true
           playbookImportFrequencySeconds: 86400
@@ -1556,6 +1563,14 @@ soc:
           reconcilePersona: ""
           toolUseTurnAttempts: 12
           toolUseTurnDelayMs: 175
+          agentSessionMaxTurns: 20
+          agentStreamFlushIntervalMs: 1000
+          agentStreamIdleTimeoutSeconds: 300
+          automationSettings:
+            tickIntervalSeconds: 60
+            maxConcurrentItems: 4
+            maxQueuedItems: 0
+            alertTriageEpoch: "2026-09-24T00:00:00Z"
           tools:
             filterEventFields:
               - "@timestamp"
@@ -2666,8 +2681,11 @@ soc:
               query: "so_detection.language:suricata | groupby so_detection.ruleset so_detection.isEnabled | groupby so_detection.category"
               description: Show all NIDS Detections, which are run with Suricata
             - name: "Detection Type - Sigma (Elastalert) - All"
-              query: "so_detection.language:sigma | groupby so_detection.ruleset so_detection.isEnabled | groupby so_detection.category | groupby so_detection.product"
+              query: "so_detection.language:sigma | groupby so_detection.ruleType | groupby so_detection.ruleset so_detection.isEnabled | groupby so_detection.category | groupby so_detection.product"
               description: Show all Sigma Detections, which are run with Elastalert
+            - name: "Detection Type - Sigma (Elastalert) - Correlations"
+              query: "so_detection.ruleType:correlation | groupby so_detection.correlationType so_detection.isEnabled | groupby so_detection.correlationTimespan | groupby so_detection.ruleset"
+              description: Show Sigma correlation Detections
             - name: "Detection Type - YARA (Strelka)"
               query: "so_detection.language:yara | groupby so_detection.ruleset so_detection.isEnabled"
               description: Show all YARA detections, which are used by Strelka
@@ -2751,7 +2769,7 @@ soc:
             elastalert: |
               # This is a Sigma rule template, which uses YAML. Replace all template values with your own values.
               # The id (UUIDv4) is pregenerated and can safely be used.
-              # Click "Convert" to convert the Sigma rule to use Security Onion field mappings within an EQL query
+              # Click "Convert" to convert the Sigma rule to use Security Onion field mappings within a backend query
               #
               # Rule Creation Guide: https://github.com/SigmaHQ/sigma/wiki/Rule-Creation-High%E2%80%90Level-Guide
               # Logsources: https://sigmahq.io/docs/basics/log-sources.html
@@ -2781,6 +2799,58 @@ soc:
                           - ' -priv'
                   condition: all of selection_*
               level: 'high'  # info | low | medium | high | critical
+            elastalert_correlation: |
+              # Sigma correlation rule; requires ES|QL (useEsql).
+              # The first document is the correlation (id, title, severity); the documents after it are the rules it refers to, all in this Detection.
+              #
+              # Supported types: event_count, value_count, temporal, value_sum, value_avg, value_percentile, value_median.
+              # Correlation Guide: https://sigmahq.io/docs/meta/correlations.html
+              # Logsources: https://sigmahq.io/docs/basics/log-sources.html
+
+              title: 'A Short Capitalized Title With Less Than 50 Characters'
+              id: [publicId]
+              status: 'experimental'
+              description: |
+                  Describe what the correlation finds and, importantly, why relating these
+                  events is more meaningful than either of them alone.
+              references:
+                - 'https://local.invalid'
+              author: '@SecurityOnion'
+              date: '[today]'
+              tags:
+                - detection.threat_hunting
+                - attack.technique_id
+              correlation:
+                  type: value_count
+                  rules:
+                      - example_base_rule  # matches the 'name' of the document below
+                  group-by:
+                      - source.ip
+                  # Xs, Xm, Xh, Xd or Xw.
+                  timespan: 10m
+                  condition:
+                      field: dns.query.name
+                      gte: 40
+              falsepositives:
+                - 'Describe the benign activity that also produces this pattern'
+              # Placeholders: %count%, %start%, %end%, %duration%, and group-by or field values.
+              summary: '%count% distinct names queried by %source.ip% in %duration%'
+              level: 'medium'  # info | low | medium | high | critical
+              ---
+              title: 'Base Event'
+              # The correlation refers to this rule by 'name' (or by 'id').
+              name: example_base_rule
+              description: 'The single event that the correlation aggregates.'
+              logsource:
+                category: network
+                service: dns
+              detection:
+                  selection:
+                      dns.query.name|exists: true
+                  condition: selection
+              # Carried into the alert.
+              fields:
+                - dns.query.name
         assistant:
           enabled: false
           investigationPrompt: Investigate Alert ID {socId}
@@ -2794,7 +2864,7 @@ soc:
             - id: sonnet
               displayName: Claude Sonnet
               origin: USA
-              contextLimitSmall: 200000
+              contextLimitSmall: 1000000
               contextLimitLarge: 1000000
               lowBalanceColorAlert: 500000
               enabled: true

salt/soc/dyanno/hypervisor/init.sls

@@ -18,8 +18,8 @@ hypervisor_annotation:
     - name: /opt/so/saltstack/default/salt/hypervisor/soc_hypervisor.yaml
     - source: salt://soc/dyanno/hypervisor/soc_hypervisor.yaml.jinja
     - template: jinja
-    - user: socore
-    - group: socore
+    - user: root
+    - group: root
     - defaults:
         HYPERVISORS: {{ HYPERVISORS }}
         baseDomainStatus: {{ salt['pillar.get']('baseDomain:status', 'Initialized') }}

salt/soc/enabled.sls

@@ -23,7 +23,9 @@ so-soc:
     - name: so-soc
     - networks:
       - sobridge:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-soc'].ip }}
+        - ipv4_address: {{ DOCKERMERGED.containers['so-soc'].ips['sobridge'] }}
+      - soauth:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-soc'].ips['soauth'] }}
     - binds:
       - /nsm/rules:/nsm/rules:rw
       - /opt/so/conf/strelka:/opt/sensoroni/yara:rw
@@ -45,9 +47,8 @@ so-soc:
 {% endif %}
       - /opt/so/conf/soc/motd.md:/opt/sensoroni/html/motd.md:ro
       - /opt/so/conf/soc/banner.md:/opt/sensoroni/html/login/banner.md:ro
-      - /opt/so/conf/soc/sigma_so_pipeline.yaml:/opt/sensoroni/sigma_so_pipeline.yaml:ro
+      - /opt/so/conf/soc/sigma_pipelines:/opt/sensoroni/sigma_pipelines:ro
       - /opt/so/conf/soc/sigma_playbook_pipeline.yaml:/opt/sensoroni/sigma_playbook_pipeline.yaml:ro
-      - /opt/so/conf/soc/sigma_final_pipeline.yaml:/opt/sensoroni/sigma_final_pipeline.yaml:ro
       - /opt/so/conf/soc/playbook_placeholder_map.yaml:/opt/sensoroni/playbook_placeholder_map.yaml:ro
       - /opt/so/conf/soc/playbook_placeholder_map_custom.yaml:/opt/sensoroni/playbook_placeholder_map_custom.yaml:ro
       - /opt/so/conf/soc/custom.js:/opt/sensoroni/html/js/custom.js:ro
@@ -105,6 +106,7 @@ so-soc:
       - file: socclientsroles
       - file: socplaybookplaceholdermap
       - file: socplaybookplaceholdermapcustom
+      - file: socsigmapipelines
 
 delete_so-soc_so-status.disabled:
   file.uncomment:

salt/soc/files/soc/sigma_pipelines/sigma_esql_pipeline.yml

@@ -0,0 +1,477 @@
+name: Security Onion ES|QL Pipeline
+# ES|QL query settings
+priority: 92
+transformations:
+    - id: esql_default_index
+      type: set_state
+      key: index
+      val: .ds-logs-*
+    - id: esql_source_metadata
+      type: set_state
+      key: metadata
+      val: "_id, _index, _source"
+    - id: esql_source_keep
+      type: set_state
+      key: keep
+      val: "_id, _index, _source"
+    # unmapped fields read as null instead of failing the query
+    - id: esql_unmapped_fields
+      type: set_state
+      key: unmapped_fields
+      val: nullify
+    # FROM targets per logsource, any namespace; later entries win, correlations get the union
+    - id: esql_index_process_creation
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.process-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-system.security-*
+        - .ds-logs-windows.powershell-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-auditd_manager.auditd-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        category: process_creation
+    - id: esql_index_process_creation_windows
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.process-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-system.security-*
+        - .ds-logs-windows.powershell-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: process_creation
+    - id: esql_index_process_creation_linux
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.process-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-auditd_manager.auditd-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: linux
+        category: process_creation
+    - id: esql_index_process_creation_macos
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.process-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: macos
+        category: process_creation
+    - id: esql_index_file
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.file-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: file_event
+      - type: logsource
+        category: file_delete
+      - type: logsource
+        category: file_rename
+      - type: logsource
+        category: file_change
+      - type: logsource
+        category: file_access
+    - id: esql_index_file_windows
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.file-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: file_event
+      - type: logsource
+        product: windows
+        category: file_delete
+      - type: logsource
+        product: windows
+        category: file_rename
+      - type: logsource
+        product: windows
+        category: file_change
+      - type: logsource
+        product: windows
+        category: file_access
+    - id: esql_index_file_linux
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.file-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: linux
+        category: file_event
+      - type: logsource
+        product: linux
+        category: file_delete
+      - type: logsource
+        product: linux
+        category: file_rename
+      - type: logsource
+        product: linux
+        category: file_change
+      - type: logsource
+        product: linux
+        category: file_access
+    - id: esql_index_file_macos
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.file-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: macos
+        category: file_event
+      - type: logsource
+        product: macos
+        category: file_delete
+      - type: logsource
+        product: macos
+        category: file_rename
+      - type: logsource
+        product: macos
+        category: file_change
+      - type: logsource
+        product: macos
+        category: file_access
+    - id: esql_index_registry
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.registry-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: registry_set
+      - type: logsource
+        category: registry_add
+      - type: logsource
+        category: registry_delete
+      - type: logsource
+        category: registry_event
+    - id: esql_index_library
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.library-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: image_load
+      - type: logsource
+        category: driver_load
+    - id: esql_index_endpoint_network
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: network_connection
+      - type: logsource
+        category: dns_query
+    - id: esql_index_endpoint_network_windows
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: network_connection
+      - type: logsource
+        product: windows
+        category: dns_query
+    - id: esql_index_endpoint_network_linux
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: linux
+        category: network_connection
+      - type: logsource
+        product: linux
+        category: dns_query
+    - id: esql_index_endpoint_network_macos
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: macos
+        category: network_connection
+      - type: logsource
+        product: macos
+        category: dns_query
+    - id: esql_index_sysmon_only
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: process_access
+      - type: logsource
+        category: create_remote_thread
+      - type: logsource
+        category: pipe_created
+      - type: logsource
+        category: create_stream_hash
+      - type: logsource
+        category: wmi_event
+      - type: logsource
+        category: raw_access_thread
+      - type: logsource
+        category: process_tampering
+      - type: logsource
+        category: sysmon_status
+      - type: logsource
+        category: sysmon_error
+      - type: logsource
+        category: file_executable_detected
+      - type: logsource
+        category: file_block_executable
+      - type: logsource
+        category: file_block_shredding
+      - type: logsource
+        category: clipboard_capture
+      - type: logsource
+        product: windows
+        service: sysmon
+    - id: esql_index_ps_operational
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-windows.powershell_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: ps_script
+      - type: logsource
+        category: ps_module
+      - type: logsource
+        product: windows
+        service: powershell
+    - id: esql_index_ps_classic
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-windows.powershell-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: ps_classic_start
+      - type: logsource
+        category: ps_classic_provider_start
+      - type: logsource
+        category: ps_classic_script
+      - type: logsource
+        product: windows
+        service: powershell-classic
+    - id: esql_index_win_security
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.security-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: windows
+        service: security
+    - id: esql_index_win_system
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.system-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: windows
+        service: system
+    - id: esql_index_win_application
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.application-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: windows
+        service: application
+    - id: esql_index_linux_auth
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.auth-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: linux
+        service: auth
+      - type: logsource
+        product: linux
+        service: sshd
+      - type: logsource
+        product: linux
+        service: sudo
+    - id: esql_index_linux_syslog
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.syslog-*
+        - .ds-logs-syslog-so-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: linux
+        service: syslog
+    - id: esql_index_linux_auditd
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-auditd_manager.auditd-*
+        - .ds-logs-auditd.log-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: linux
+        service: auditd
+    - id: esql_index_network
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-zeek-so-*
+        - .ds-logs-suricata-so-*
+        - .ds-logs-suricata.alerts-so-*
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        category: network
+    - id: esql_index_so_network
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-zeek-so-*
+        - .ds-logs-suricata-so-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: network
+        service: connection
+      - type: logsource
+        category: network
+        service: dns
+      - type: logsource
+        category: network
+        service: http
+      - type: logsource
+        category: network
+        service: file
+      - type: logsource
+        category: network
+        service: x509
+      - type: logsource
+        category: network
+        service: ssl
+      - type: logsource
+        category: network
+        service: ssh
+      - type: logsource
+        category: dns
+    - id: esql_index_zeek
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-zeek-so-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: zeek
+    - id: esql_index_opencanary
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-idh-so-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: opencanary
+    - id: esql_index_kratos
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-kratos-so-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: kratos
+

salt/soc/files/soc/sigma_pipelines/sigma_so_pipeline.yml

@@ -1,6 +1,38 @@
 name: Security Onion Baseline Pipeline
 priority: 90
 transformations:
+    # ES|QL scalar == returns null on multivalued fields; the
+    # backend reads this key and emits MV_INTERSECTS instead.
+    - id: declare_multivalue_fields
+      type: set_state
+      key: multivalue_fields
+      val:
+        - event.type
+        - event.action
+        - event.category
+        - tags
+        - process.args
+        - related.ip
+        - dns.resolved_ip
+    # Always lowercase, so matched exactly; the backend can then use the indexed ':' operator.
+    - id: case_sensitive_categorization_fields
+      type: set_state
+      key: case_insensitive_exempt_fields
+      val:
+        - tags
+        - event.category
+        - event.type
+        - event.kind
+    # Not every source maps .caseless; EQL/ES|QL already match case-insensitively.
+    - id: caseless_to_parent_fields
+      type: field_name_mapping
+      mapping:
+        process.executable.caseless: process.executable
+        process.name.caseless: process.name
+        process.parent.executable.caseless: process.parent.executable
+        process.parent.name.caseless: process.parent.name
+        target.process.executable.caseless: target.process.executable
+        target.process.name.caseless: target.process.name
     - id: baseline_field_name_mapping
       type: field_name_mapping
       mapping:
@@ -95,6 +127,9 @@ transformations:
       valid_hash_algos: ["MD5", "SHA1", "SHA256", "SHA512", "IMPHASH"]
       field_prefix: "file"
       drop_algo_prefix: False
+      # ecs_windows has already renamed Hashes; pySigma 1.5+ only parses the fields listed here
+      field_to_parse:
+        - winlog.event_data.Hashes
       field_name_conditions:
         - type: include_fields
           fields:

salt/soc/files/soc/sigma_playbook_pipeline.yaml

@@ -2,13 +2,13 @@ name: Security Onion - Playbook Pipeline
 priority: 97
 transformations:
     # Route to lowercase-normalized .caseless subfields for case-insensitive matching.
-    # file.path.caseless exists on Defend only (Sysmon file events lack it);
     # registry.path / dll.path / file.name have no .caseless on any source.
     - id: case_insensitive_string_fields
       type: field_name_mapping
       mapping:
         process.executable: process.executable.caseless
         process.parent.executable: process.parent.executable.caseless
+        process.parent.name: process.parent.name.caseless
         process.command_line: process.command_line.caseless
         process.parent.command_line: process.parent.command_line.caseless
         file.path: file.path.caseless

salt/soc/merged.map.jinja

@@ -8,6 +8,7 @@
 {% from 'elasticsearch/config.map.jinja' import ELASTICSEARCH_NODES %}
 {% from 'manager/map.jinja' import MANAGERMERGED %}
 {% from 'telegraf/map.jinja' import TELEGRAFMERGED %}
+{% from 'elastalert/map.jinja' import ELASTALERTMERGED %}
 {%- set PG_ENTRY = salt['pillar.get']('telegraf:postgres_creds:' ~ grains.id, {}) %}
 {%- set PG_USER = PG_ENTRY.get('user', '') %}
 {%- set PG_PASS = PG_ENTRY.get('pass', '') %}
@@ -63,6 +64,10 @@
 {%   do SOCMERGED.config.server.modules.elastalertengine.update({'enabledSigmaRules': SOCMERGED.config.server.modules.elastalertengine.enabledSigmaRules.default}) %}
 {% endif %}
 
+{# correlation schedules follow ElastAlert's run_every #}
+{% set run_every = ELASTALERTMERGED.config.run_every %}
+{% do SOCMERGED.config.server.modules.elastalertengine.update({'elastAlertRunEverySeconds': run_every.get('minutes', 0) * 60 + run_every.get('seconds', 0)}) %}
+
 {# set elastalertengine.rulesRepos, strelkaengine.rulesRepos, and suricataengine.rulesetSources based on airgap or not #}
 {% if GLOBALS.airgap %}
 {%   do SOCMERGED.config.server.modules.elastalertengine.update({'rulesRepos': SOCMERGED.config.server.modules.elastalertengine.rulesRepos.airgap}) %}
@@ -80,6 +85,18 @@
 {%   do SOCMERGED.config.server.update({'airgapEnabled': false}) %}
 {% endif %}
 
+{# Sigma correlations require ES|QL: load the community correlations and offer correlation authoring only when it is on #}
+{% set use_esql = SOCMERGED.config.server.modules.elastalertengine.useEsql %}
+{% for repo in SOCMERGED.config.server.modules.elastalertengine.rulesRepos %}
+{%   if repo.get('rulesetName') == 'securityonion-resources' and repo.get('folder') in ['sigma', 'sigma/stable'] %}
+{%     do repo.update({'folder': 'sigma' if use_esql else 'sigma/stable'}) %}
+{%   endif %}
+{% endfor %}
+{% if not use_esql %}
+{%   do SOCMERGED.config.server.client.detection.templateDetections.pop('elastalert_correlation', None) %}
+{%   do SOCMERGED.config.server.client.detections.update({'queries': SOCMERGED.config.server.client.detections.queries | rejectattr('name', 'equalto', 'Detection Type - Sigma (Elastalert) - Correlations') | list}) %}
+{% endif %}
+
 {# Define the postgresmetrics module if telegraf is setup to only use Postgres #}
 {% if TELEGRAFMERGED.output != 'INFLUXDB' and PG_USER and PG_PASS %}
 {%   do SOCMERGED.config.server.modules.update({

salt/soc/soc_soc.yaml

@@ -155,6 +155,15 @@ soc:
         description: Path to custom markdown templates for PDF report generation. All markdown files in this directory will be available as custom reports in the SOC Reports interface.
         global: True
         advanced: True
+      schedules:
+        title: Schedules
+        description: Schedules that are shared across the Security Onion product. Modify via one of the SOC Schedules view.
+        readonlyUi: True
+        global: True
+        advanced: True
+        forcedType: string
+        syntax: json
+        storage: db
       subgrids:
         title: Subordinate Grids
         description: |
@@ -392,10 +401,27 @@ soc:
             advanced: False
             helpLink: sigma
           useEsql:
-            description: "(Pre-release) Use Elasticsearch Piped Query Language (ES|QL) instead of EQL (Elastic Query Language) for Elasticsearch queries. The Sigma converter will output ES|QL instead of EQL, allowing support for correlations."
+            description: "(Pre-release) Use Elasticsearch Piped Query Language (ES|QL) instead of EQL (Elastic Query Language) for Elasticsearch queries. The Sigma converter will output ES|QL instead of EQL, allowing support for correlations. Switching back to EQL is not supported for correlations."
             global: True
             advanced: True
             forcedType: bool
+          esqlCaseInsensitive:
+            description: "Match string values case-insensitively when converting Sigma rules. Applies to ES|QL only"
+            global: True
+            advanced: True
+            forcedType: bool
+          esqlQueryDelaySeconds:
+            description: "Seconds ES|QL rules search behind now, so unsearchable events aren't missed. Delays alerts by the same amount. Set at least the longest index refresh interval. ES|QL only."
+            global: True
+            advanced: True
+            forcedType: int
+            helpLink: sigma
+          esqlCorrelationAllowanceSeconds:
+            description: "Extra seconds of arrivals each correlation run re-reads beyond its timespan, so a burst whose events arrive spread out is still counted together. ES|QL only."
+            global: True
+            advanced: True
+            forcedType: int
+            helpLink: sigma
         elastic:
           index:
             description: Comma-separated list of indices or index patterns (wildcard "*" supported) that SOC will search for records.
@@ -476,6 +502,29 @@ soc:
             global: True
             advanced: True
             forcedType: bool
+        notification:
+          destinations:
+            title: Notification Destinations
+            description: JSON list of notifications. Modify via the SOC Notifications view.
+            readonlyUi: True
+            global: True
+            advanced: True
+            forcedType: string
+            syntax: json
+            storage: db
+          dismissedPruneDays:
+            title: Dismissed Retention Days
+            description: The number of days to retain dismissed notifications. When a notification is dismissed, it will be pruned after this many days. Only one user need dismiss a notification for it to be pruned.
+            forcedType: int
+            global: True
+          maxListLimit:
+            description: Maximum number of notifications to display.
+            forcedType: int
+            global: True
+          enabled:
+            description: Enables or disables the SOC notification module.
+            forcedType: bool
+            global: True
         postgres:
           host:
             description: Hostname or IP address of the PostgreSQL server used by SOC. Defaults to the manager hostname.
@@ -502,6 +551,48 @@ soc:
             global: True
             sensitive: True
             advanced: True
+        postgresmetrics:
+          host:
+            description: Hostname or IP address of the PostgreSQL server used by Telegraf. Defaults to the manager hostname.
+            global: True
+            advanced: True
+          port:
+            description: Port of the PostgreSQL server used by Telegraf.
+            global: True
+            advanced: True
+          sslMode:
+            description: "Use encrypted connections to the PostgreSQL server used by Telegraf. Must be one of the following values: disable, allow, prefer, require, verify-ca, verify-full."
+            global: True
+            advanced: True
+          database:
+            description: Database to authenticate to on the PostgreSQL server.
+            global: True
+            advanced: True
+          user:
+            description: Username to authenticate to the PostgreSQL server used by Telegraf.
+            global: True
+            advanced: True
+          password:
+            description: Password used to authenticate to the PostgreSQL server used by Telegraf.
+            global: True
+            sensitive: True
+            advanced: True
+          cacheExpirationMs:
+            description: The interval (in milliseconds) to wait before querying the DB for updated metrics.
+            global: True
+            advanced: True
+          maxMetricAgeSeconds:
+            description: The maximum age (in seconds) of metrics to display in the SOC Grid Metrics view. Metrics older than this value will not be displayed.
+            global: True
+            advanced: True
+          alarms:
+            description: JSON list of metric alarms. Modify via the SOC Grid Alarms view.
+            readonlyUi: True
+            advanced: True
+            global: True
+            forcedType: string
+            syntax: json
+            storage: db
         salt:
           longRelayTimeoutMs:
             description: Duration (in milliseconds) to wait for a response from the Salt API when executing tasks known for being long running before giving up and showing an error on the SOC UI.
@@ -760,6 +851,7 @@ soc:
                 - gemini
                 - openai_responses
                 - openai_chat
+                - openai_embeddings
             - field: apiUrl
               label: API URL
               required: False
@@ -781,6 +873,15 @@ soc:
             description: Indicates if the Assistant Module should operate in agentic mode or not. If true, agents can work together to solve tasks.
             global: True
             forcedType: bool
+          automations:
+            description: Scheduled automations for the Onion AI assistant, managed from the Agent Studio.
+            global: True
+            advanced: True
+            readonlyUi: True
+            storage: db
+            forcedType: string
+            syntax: json
+            helpLink: onion-ai
           agents:
             description: Agent definitions for the Onion AI assistant, managed from the Agent Studio. An entry naming a system agent overrides only the fields an admin may change; everything else comes from the built-in definition.
             global: True
@@ -813,6 +914,9 @@ soc:
             - field: persona
               label: Persona
               multiline: True
+            - field: maxConcurrentInstances
+              label: Max Concurrent Instances
+              forcedType: int
           skills:
             description: Skill definitions for the Onion AI assistant, managed from the Agent Studio. An entry naming a system skill overrides only its enabled state and persona addendum; its tool set comes from the built-in definition.
             global: True
@@ -916,6 +1020,43 @@ soc:
             description: The number of times to retry extracting memories from a session if errors occur.
             global: True
             advanced: True
+          agentSessionMaxTurns:
+            description: Maximum number of model turns a headless agent session, such as one started by an automation, may take before it is stopped. Turns taken by delegated sub-agents count toward this limit. A session that reaches the limit is recorded as failed.
+            global: True
+            advanced: True
+            forcedType: int
+          agentStreamFlushIntervalMs:
+            description: Milliseconds between writes of a streaming headless agent turn to the database. Lower values show progress sooner in the Agent Studio at the cost of more frequent Elasticsearch updates.
+            global: True
+            advanced: True
+            forcedType: int
+          agentStreamIdleTimeoutSeconds:
+            description: Seconds a streaming headless agent turn may go without receiving any output before it is abandoned and the session is recorded as failed. Set to 0 to disable the timeout.
+            global: True
+            advanced: True
+            forcedType: int
+          automationSettings:
+            tickIntervalSeconds:
+              description: How often, in seconds, the automation scheduler checks for automations that are due to run. Must be greater than 0.
+              global: True
+              advanced: True
+              forcedType: int
+            maxConcurrentItems:
+              description: Maximum number of automation work items that may run at the same time. Additional work items wait in the queue until a running item finishes. User chat sessions count toward this limit but are never held back by it. Set to 0 to disable the limit.
+              global: True
+              advanced: True
+              forcedType: int
+            maxQueuedItems:
+              description: Maximum number of automation work items that may wait to start. Once the queue is full, no new work items are created until the backlog drains. Set to 0 to disable the limit.
+              global: True
+              advanced: True
+              forcedType: int
+            alertTriageEpoch:
+              description: The earliest alert time the Alert Triage automation will consider. Alerts before this time are never triaged, which keeps a first run on an existing deployment from working through old history. Must be in UTC format (2026-09-24T00:00:00Z).
+              regex: '^(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?Z)?$'
+              regexFailureMessage: Expecting date in RFC3339 format (2026-09-24T00:00:00Z)
+              global: True
+              advanced: True
           tools:
             filterEventFields:
               description: A whitelist of fields to return when OnionAI uses the query_events tool. All other fields are removed. One field per line.

salt/strelka/config.sls

@@ -51,8 +51,8 @@ strelka_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://strelka/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 {% else %}

salt/suricata/config.sls

@@ -64,6 +64,7 @@ suricata:
     - gid: 940
     - home: /nsm/suricata
     - createhome: False
+    - shell: /sbin/nologin
 
 socoregroupwithsuricata:
   group.present:
@@ -76,16 +77,16 @@ suricata_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://suricata/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 suricata_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://suricata/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
 

salt/telegraf/config.sls

@@ -36,7 +36,7 @@ tgraf_sync_script_{{script}}:
     - name: /opt/so/conf/telegraf/scripts/{{script}}
     - user: root
     - group: 939
-    - mode: 770
+    - mode: 750
     - template: jinja
     - source: salt://telegraf/scripts/{{script}}
     - defaults:
@@ -49,7 +49,7 @@ tgraf_sync_script_esindexsize.sh:
     - name: /opt/so/conf/telegraf/scripts/esindexsize.sh
     - user: root
     - group: 939
-    - mode: 770
+    - mode: 750
     - source: salt://telegraf/scripts/esindexsize.sh
 {# Copy conf/elasticsearch/curl.config for telegraf to use with esindexsize.sh #}
 tgraf_sync_escurl_conf:
@@ -61,22 +61,102 @@ tgraf_sync_escurl_conf:
     - source: salt://elasticsearch/curl.config
 {% endif %}
 
+# so-container-stats runs on the host as somon, a docker group member, so the container does
+# not need the docker socket
+somongroup:
+  group.present:
+    - name: somon
+    - gid: 961
+
+# cron chdirs to $HOME before running a job, so home must exist
+somon:
+  user.present:
+    - uid: 961
+    - gid: 961
+    - home: /opt/so/log/somon
+    - createhome: False
+    - shell: /sbin/nologin
+    - groups:
+      - docker
+    # renumbering an existing somon is a no-op on a fresh host and lets a host created
+    # before the id changed converge instead of failing the whole telegraf state
+    - allow_uid_change: True
+    - allow_gid_change: True
+    - require:
+      - group: somongroup
+
+somonlogdir:
+  file.directory:
+    - name: /opt/so/log/somon
+    - user: 961
+    - group: 961
+    - mode: 755
+    # the lock file is not otherwise managed; recurse so a renumber rechowns it too
+    - recurse:
+      - user
+      - group
+    - require:
+      - user: somon
+
+containers_log:
+  file.managed:
+    - name: /opt/so/log/somon/containers.log
+    - user: 961
+    - group: 961
+    - mode: 644
+    - replace: False
+    - require:
+      - file: somonlogdir
+
+# telegraf reads on the same minute boundary the collector runs, and docker stats takes
+# seconds, so write aside and rename rather than truncating the file telegraf is reading.
+# ; not && so a failed run replaces the file instead of leaving stale metrics behind.
+# flock -n keeps a run that outlives its minute from racing the next one over the same tmp
+# file; the skipped run leaves a stale containers.log, which containers.sh discards by age
+so-container-stats_cron:
+  cron.present:
+    - name: "flock -n /opt/so/log/somon/containers.lock -c '/usr/sbin/so-container-stats > /opt/so/log/somon/containers.log.tmp 2>&1; mv -f /opt/so/log/somon/containers.log.tmp /opt/so/log/somon/containers.log'"
+    - identifier: so-container-stats_cron
+    - user: somon
+    - minute: '*/1'
+    - hour: '*'
+    - daymonth: '*'
+    - month: '*'
+    - dayweek: '*'
+    - require:
+      - user: somon
+
+# salt.lasthighstate touches this at order 9001, after the container starts; pre-create it so
+# docker does not create a directory at the bind mount source
+lasthighstate_placeholder:
+  file.managed:
+    - name: /opt/so/log/salt/lasthighstate
+    - mode: 644
+    - replace: False
+    - makedirs: True
+
 telegraf_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://telegraf/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
-#telegraf_sbin_jinja:
-#  file.recurse:
-#    - name: /usr/sbin
-#    - source: salt://telegraf/tools/sbin_jinja
-#    - user: 939
-#    - group: 939 
-#    - file_mode: 755
-#    - template: jinja
+# so-container-stats needs the per-stat toggles, so it renders instead of copying
+tgraf_sbin_jinja:
+  file.recurse:
+    - name: /usr/sbin
+    - source: salt://telegraf/tools/sbin_jinja
+    - user: root
+    - group: root
+    - file_mode: 755
+    # the unit test lives beside the script; it must not ship or be rendered as jinja
+    - exclude_pat:
+      - "*_test.py"
+    - template: jinja
+    - defaults:
+        CONTAINER_STATS: {{ TELEGRAFMERGED.container_stats }}
 
 tgrafconf:
   file.managed:

salt/telegraf/defaults.yaml

@@ -10,6 +10,69 @@ telegraf:
     flush_jitter: '0s'
     debug: false
     quiet: false
+  container_stats:
+    tags:
+      identity: False
+    engine:
+      n_containers: False
+      n_containers_running: False
+      n_containers_stopped: False
+      n_containers_paused: False
+      n_images: False
+      n_cpus: False
+      n_goroutines: False
+      n_used_file_descriptors: False
+      n_listener_events: False
+      memory_total: False
+    cpu:
+      usage_percent: True
+      usage_total: False
+      usage_in_usermode: False
+      usage_in_kernelmode: False
+      usage_system: False
+      throttling_periods: False
+      throttling_throttled_periods: False
+      throttling_throttled_time: False
+      container_id: False
+    mem:
+      usage_percent: True
+      usage: False
+      limit: False
+      max_usage: False
+      active_anon: False
+      active_file: False
+      inactive_anon: False
+      inactive_file: False
+      unevictable: False
+      pgfault: False
+      pgmajfault: False
+      container_id: False
+    net:
+      rx_bytes: True
+      rx_packets: False
+      rx_errors: False
+      rx_dropped: False
+      tx_bytes: False
+      tx_packets: False
+      tx_errors: False
+      tx_dropped: False
+      container_id: False
+    blkio:
+      io_service_bytes_recursive_read: False
+      io_service_bytes_recursive_write: False
+      container_id: False
+    status:
+      uptime_ns: True
+      oomkilled: True
+      pid: False
+      exitcode: False
+      restart_count: False
+      started_at: False
+      finished_at: False
+      container_id: False
+    health:
+      health_status: False
+      failing_streak: False
   scripts:
     eval:
       - agentstatus.sh
@@ -19,6 +82,7 @@ telegraf:
       - oldpcap.sh
       - os.sh
       - raid.sh
+      - containers.sh
       - sostatus.sh
       - suriloss.sh
       - surirules.sh
@@ -34,6 +98,7 @@ telegraf:
       - os.sh
       - raid.sh
       - redis.sh
+      - containers.sh
       - sostatus.sh
       - suriloss.sh
       - surirules.sh
@@ -47,6 +112,7 @@ telegraf:
       - os.sh
       - raid.sh
       - redis.sh
+      - containers.sh
       - sostatus.sh
       - features.sh
     managerhype:
@@ -56,6 +122,7 @@ telegraf:
       - os.sh
       - raid.sh
       - redis.sh
+      - containers.sh
       - sostatus.sh
       - features.sh
     managersearch:
@@ -66,12 +133,14 @@ telegraf:
       - os.sh
       - raid.sh
       - redis.sh
+      - containers.sh
       - sostatus.sh
       - features.sh
     import:
       - influxdbsize.sh
       - lasthighstate.sh
       - os.sh
+      - containers.sh
       - sostatus.sh
     sensor:
       - checkfiles.sh
@@ -79,6 +148,7 @@ telegraf:
       - oldpcap.sh
       - os.sh
       - raid.sh
+      - containers.sh
       - sostatus.sh
       - suriloss.sh
       - surirules.sh
@@ -93,6 +163,7 @@ telegraf:
       - os.sh
       - raid.sh
       - redis.sh
+      - containers.sh
       - sostatus.sh
       - suriloss.sh
       - surirules.sh
@@ -101,12 +172,14 @@ telegraf:
     idh:
       - lasthighstate.sh
       - os.sh
+      - containers.sh
       - sostatus.sh
     searchnode:
       - eps.sh
       - lasthighstate.sh
       - os.sh
       - raid.sh
+      - containers.sh
       - sostatus.sh
       - features.sh
     receiver:
@@ -115,16 +188,20 @@ telegraf:
       - os.sh
       - raid.sh
       - redis.sh
+      - containers.sh
       - sostatus.sh
     fleet:
       - lasthighstate.sh
       - os.sh
+      - containers.sh
       - sostatus.sh
     hypervisor:
       - lasthighstate.sh
       - os.sh
+      - containers.sh
       - sostatus.sh
     desktop:
       - lasthighstate.sh
       - os.sh
+      - containers.sh
       - sostatus.sh

salt/telegraf/disabled.sls

@@ -13,6 +13,11 @@ so-telegraf:
   docker_container.absent:
     - force: True
 
+so-container-stats_cron:
+  cron.absent:
+    - identifier: so-container-stats_cron
+    - user: somon
+
 so-telegraf_so-status.disabled:
   file.comment:
     - name: /opt/so/conf/so-status/so-status.conf

salt/telegraf/enabled.sls

@@ -19,8 +19,7 @@ so-telegraf:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-telegraf:{{ GLOBALS.so_version }}
     - restart_policy: unless-stopped
-    - user: 939
-    - group_add: 939,920
+    - user: 939:939
     - environment:
       - HOST_ETC=/host/etc
       - HOST_SYS=/host/sys
@@ -38,7 +37,6 @@ so-telegraf:
       - /opt/so/conf/telegraf/etc/telegraf.conf:/etc/telegraf/telegraf.conf:ro
       - /opt/so/conf/telegraf/node_config.json:/etc/telegraf/node_config.json:ro
       - /var/run/utmp:/var/run/utmp:ro
-      - /var/run/docker.sock:/var/run/docker.sock:ro
       - /:/host:ro
       - /sys:/host/sys:ro
       - /proc:/host/proc:ro
@@ -51,7 +49,8 @@ so-telegraf:
       - /opt/so/log/suricata:/var/log/suricata:ro
       - /opt/so/log/raid:/var/log/raid:ro
       - /opt/so/log/sostatus:/var/log/sostatus:ro
-      - /opt/so/log/salt:/var/log/salt:ro
+      - /opt/so/log/somon:/var/log/somon:ro
+      - /opt/so/log/salt/lasthighstate:/var/log/salt/lasthighstate:ro
       - /opt/so/log/agents:/var/log/agents:ro
       {% if GLOBALS.is_manager or GLOBALS.role == 'so-heavynode' %}
       - /opt/so/conf/telegraf/etc/escurl.config:/etc/telegraf/elasticsearch.config:ro
@@ -74,6 +73,8 @@ so-telegraf:
     {%   endfor %}
     {% endif %}
     - watch:
+      - file: tgraf_sbin_jinja
+      - file: lasthighstate_placeholder
       - file: trusttheca
       - x509: telegraf_crt
       - x509: telegraf_key
@@ -83,6 +84,8 @@ so-telegraf:
       - file: tgraf_sync_script_{{script}}
     {% endfor %}
     - require:
+      - file: lasthighstate_placeholder
+      - file: somonlogdir
       - file: trusttheca
       - x509: telegraf_crt
       - x509: telegraf_key

salt/telegraf/etc/telegraf.conf

@@ -228,13 +228,6 @@
 #   ## bond interfaces.
 #   # bond_interfaces = ["bond0"]
 
-# # Read metrics about docker containers
- [[inputs.docker]]
-#   ## Docker Endpoint
-#   ##   To use TCP, set endpoint = "tcp://[ip]:[port]"
-#   ##   To use environment variables (ie, docker-machine), set endpoint = "ENV"
-   endpoint = "unix:///var/run/docker.sock"
-#
 
 # # Read stats from one or more Elasticsearch servers or clusters
 {%- if GLOBALS.is_manager or GLOBALS.role == 'so-heavynode' %}
@@ -342,6 +335,17 @@
    interval = "60s"
 {%- endif %}
 
+{%- if 'containers.sh' in TELEGRAFMERGED.scripts[GLOBALS.role.split('-')[1]] %}
+{%-   do TELEGRAFMERGED.scripts[GLOBALS.role.split('-')[1]].remove('containers.sh') %}
+[[inputs.exec]]
+   commands = [
+      ["/scripts/containers.sh"]
+   ]
+   data_format = "influx"
+   timeout = "15s"
+   interval = "60s"
+{%- endif %}
+
 {%- if TELEGRAFMERGED.scripts[GLOBALS.role.split('-')[1]] | length > 0 %}
 [[inputs.exec]]
    commands = [

salt/telegraf/scripts/containers.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+#
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+
+
+# if this script isn't already running
+if [[ ! "`pidof -x $(basename $0) -o %PPID`" ]]; then
+
+    CONTAINERSLOG=/var/log/somon/containers.log
+    # the collector rewrites this every minute; report nothing rather than repeating a stale
+    # file as if it were current, in case a run was skipped or the collector is wedged
+    MAXAGE=150
+
+    if [ -r "$CONTAINERSLOG" ]; then
+        AGE=$(( $(date +%s) - $(stat -c %Y "$CONTAINERSLOG") ))
+        if [ "$AGE" -le "$MAXAGE" ]; then
+            cat $CONTAINERSLOG
+        fi
+    fi
+
+    exit 0
+
+fi
+
+exit 0

salt/telegraf/scripts/lasthighstate.sh

@@ -8,10 +8,12 @@
 # if this script isn't already running
 if [[ ! "`pidof -x $(basename $0) -o %PPID`" ]]; then
 
-    LAST_HIGHSTATE_END=$([ -e "/var/log/salt/lasthighstate" ] && date -r /var/log/salt/lasthighstate +%s || echo 0)
-    NOW=$(date +%s)
-    HIGHSTATE_AGE_SECONDS=$((NOW-LAST_HIGHSTATE_END))
-    echo "salt highstate_age_seconds=$HIGHSTATE_AGE_SECONDS"
+    if [ -r "/var/log/salt/lasthighstate" ]; then
+        LAST_HIGHSTATE_END=$(date -r /var/log/salt/lasthighstate +%s)
+        NOW=$(date +%s)
+        HIGHSTATE_AGE_SECONDS=$((NOW-LAST_HIGHSTATE_END))
+        echo "salt highstate_age_seconds=$HIGHSTATE_AGE_SECONDS"
+    fi
 
 fi
 

salt/telegraf/soc_telegraf.yaml

@@ -53,6 +53,319 @@ telegraf:
       forcedType: bool
       advanced: True
       helpLink: influxdb
+  container_stats:
+    tags:
+      identity:
+        description: Adds the container_image, container_version, engine_host and server_version tags to every container measurement, as the retired inputs.docker plugin did. Increases series cardinality. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+    engine:
+      n_containers:
+        description: Total number of containers known to the Docker engine, running or not. Part of the engine-level docker measurement. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      n_containers_running:
+        description: Number of containers currently running. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      n_containers_stopped:
+        description: Number of containers currently stopped. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      n_containers_paused:
+        description: Number of containers currently paused. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      n_images:
+        description: Number of container images held by the Docker engine. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      n_cpus:
+        description: Number of CPUs the Docker engine reports for this host. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      n_goroutines:
+        description: Number of goroutines inside the Docker daemon. Diagnostic detail for the daemon itself. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      n_used_file_descriptors:
+        description: Number of file descriptors held open by the Docker daemon. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      n_listener_events:
+        description: Number of event listeners subscribed to the Docker daemon. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      memory_total:
+        description: Total physical memory the Docker engine reports for this host, in bytes. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+    cpu:
+      usage_percent:
+        description: Percentage of host CPU consumed by the container. Required by the Container CPU Usage chart on the Security Onion Performance dashboard.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      usage_total:
+        description: Cumulative CPU time consumed by the container, in nanoseconds. Read from the cgroup. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      usage_in_usermode:
+        description: Cumulative CPU time consumed in user mode, in nanoseconds. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      usage_in_kernelmode:
+        description: Cumulative CPU time consumed in kernel mode, in nanoseconds. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      usage_system:
+        description: Cumulative host-wide CPU time, in nanoseconds. Used as the denominator when calculating container CPU percentage. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      throttling_periods:
+        description: Number of CPU enforcement periods the container has seen. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      throttling_throttled_periods:
+        description: Number of periods in which the container was throttled against its CPU limit. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      throttling_throttled_time:
+        description: Total time the container spent throttled, in nanoseconds. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      container_id: &containerid
+        description: Full 64 character container ID, emitted as a field on this measurement. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+    mem:
+      usage_percent:
+        description: Percentage of its memory limit the container is using. Required by the Container Memory Usage chart on the Security Onion Performance dashboard.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      usage:
+        description: Container memory usage in bytes, excluding reclaimable page cache. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      limit:
+        description: Memory limit for the container in bytes. Reports total host memory when the container is unlimited. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      max_usage:
+        description: Peak memory usage for the container in bytes, read from the cgroup peak counter. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      active_anon:
+        description: Anonymous memory on the active LRU list, in bytes. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      active_file:
+        description: Page cache on the active LRU list, in bytes. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      inactive_anon:
+        description: Anonymous memory on the inactive LRU list, in bytes. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      inactive_file:
+        description: Page cache on the inactive LRU list, in bytes. This is the reclaimable cache subtracted from usage. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      unevictable:
+        description: Memory that cannot be reclaimed, in bytes. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      pgfault:
+        description: Cumulative number of page faults taken by the container. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      pgmajfault:
+        description: Cumulative number of major page faults, those requiring disk access. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      container_id: *containerid
+    net:
+      rx_bytes:
+        description: Bytes received by the container across all interfaces except loopback. Required by the Container Traffic - Inbound chart on the Security Onion Performance dashboard.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      rx_packets:
+        description: Packets received by the container. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      rx_errors:
+        description: Receive errors counted on the container interfaces. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      rx_dropped:
+        description: Received packets dropped by the container interfaces. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      tx_bytes:
+        description: Bytes transmitted by the container. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      tx_packets:
+        description: Packets transmitted by the container. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      tx_errors:
+        description: Transmit errors counted on the container interfaces. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      tx_dropped:
+        description: Transmitted packets dropped by the container interfaces. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      container_id: *containerid
+    blkio:
+      io_service_bytes_recursive_read:
+        description: Cumulative bytes read from block devices by the container. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      io_service_bytes_recursive_write:
+        description: Cumulative bytes written to block devices by the container. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      container_id: *containerid
+    status:
+      uptime_ns:
+        description: How long the container has been running, in nanoseconds. Required by the Container Uptime chart on the Security Onion Performance dashboard.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      oomkilled:
+        description: Whether the container was killed by the kernel out-of-memory handler. Required by the Most Recent Container Events table on the Security Onion Performance dashboard.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      pid:
+        description: Host process ID of the container main process. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      exitcode:
+        description: Exit code of the container main process. Meaningful once the container has stopped. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      restart_count:
+        description: Number of times the Docker engine has restarted this container. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      started_at:
+        description: Time the container last started, as a Unix timestamp in nanoseconds. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      finished_at:
+        description: Time the container last exited, as a Unix timestamp in nanoseconds. Absent for a container that has never exited. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      container_id: *containerid
+    health:
+      health_status:
+        description: Result of the container healthcheck, such as healthy, unhealthy or starting. Only emitted for containers that define a healthcheck. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
+      failing_streak:
+        description: Number of consecutive failed healthchecks. Only emitted for containers that define a healthcheck. Defaults to off.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: influxdb
   scripts:
     eval: &telegrafscripts
       description: List of input.exec scripts to run for this node type. The script must be present in salt/telegraf/scripts.