Wazuh Fim Investigation logo

Wazuh Fim Investigation

Organization
gensecaihq
wazuh-fim-investigation

Investigate Wazuh File Integrity Monitoring (syscheck) alerts — file and registry add/modify/delete events, checksums, permissions and who-data — separate tampering from routine change and pivot to processes and users; use for any syscheck alert or suspected persistence/tampering.

Overview

Publishergensecaihq
RepositoryWazuh-Autopilot
Skill namewazuh-fim-investigation
Stars
61
Forks
15
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by gensecaihq on GitHub. Read the source before you install it.

Installation

Install the Wazuh Fim Investigation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/gensecaihq/Wazuh-Autopilot/tree/main/backend/app/skills/wazuh-fim-investigation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/gensecaihq/Wazuh-Autopilot.git /tmp/Wazuh-Autopilot
mkdir -p .claude/skills
cp -r /tmp/Wazuh-Autopilot/backend/app/skills/wazuh-fim-investigation .claude/skills/wazuh-fim-investigation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wazuh Fim Investigation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wazuh Fim Investigation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wazuh Fim Investigation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Wazuh FIM Investigation

Wazuh FIM (syscheck) alerts on changes to monitored files and Windows registry entries. The question is always: expected change (patching, config management) or tampering/persistence?

Core syscheck rules (stock ruleset)

EventFilesWindows registry keyWindows registry value
Modifiedrule 550 (level 7)rule 594 (level 5)rule 750 (level 5)
Deletedrule 553 (level 7)rule 597 (level 5)rule 751 (level 5)
Addedrule 554 (level 5)rule 598 (level 5)rule 752 (level 5)

Groups: syscheck, plus syscheck_entry_modified / syscheck_entry_deleted / syscheck_entry_added and syscheck_file / syscheck_registry. Query by group: get_wazuh_alerts rule_groups=["syscheck"] agent_id="<id>" timestamp_start="now-24h".

FIM health signals (monitoring gaps, not attacks): rule 560 (level 7, "FIM real-time queue is full") and rule 233 (level 12, "The maximum limit of files monitored has been reached") mean changes may have been missed — record it and hand off to platform-engineer.

Key fields

FieldUse
syscheck.pathWhat changed
syscheck.eventadded / modified / deleted
syscheck.moderealtime, whodata or scheduled — scheduled scans only tell you the change happened since the last scan
syscheck.md5_before/after, sha1_*, sha256_*Content change; hashes go to threat-intel for reputation
syscheck.size_before/afterTruncation, appended payloads
syscheck.perm_before/after, uname_*, gname_*, uid_*Permission / ownership changes (e.g. SUID, world-writable)
syscheck.changed_attributesWhich attributes changed
syscheck.diffText diff (only when report_changes is enabled for the path)
syscheck.audit.user.name, .audit.effective_user.name, .audit.process.name, .audit.process.id, .audit.process.ppidWho-data: which user and process made the change (Linux auditd / Windows SACL)

If syscheck.audit.* is absent the path isn't in who-data mode — you know what changed, not who. Say so rather than guessing.

High-value paths

LinuxWhy
/etc/passwd, /etc/shadow, /etc/group, /etc/sudoers, /etc/sudoers.d/*Account creation, privilege (T1136, T1548)
/root/.ssh/authorized_keys, ~/.ssh/authorized_keysPersistence via keys (T1098.004)
/etc/crontab, /etc/cron.*, /var/spool/cron/*Scheduled persistence (T1053.003)
/etc/systemd/system/*, /lib/systemd/system/*, /etc/init.d/*Service persistence (T1543.002)
/etc/ld.so.preload, /etc/profile.d/*, ~/.bashrcHijacking / shell persistence
Web roots (/var/www/*)Web shells (T1505.003)
Binaries in /bin, /usr/bin, /usr/sbinTrojaned tools
WindowsWhy
HKLM\...\CurrentVersion\Run, RunOnce, HKCU equivalentsLogon persistence (T1547.001)
HKLM\SYSTEM\CurrentControlSet\Services\*Service creation/modification (T1543.003)
Startup foldersPersistence
C:\Windows\System32\drivers\etc\hostsTraffic redirection
C:\Windows\System32\* executablesBinary replacement

Procedure

  1. Scope: pull all syscheck alerts for the agent in the window; list changed paths.
  2. Baseline the change: check for package activity in the same window — rule 2902 (level 7, "New dpkg (Debian Package) installed"), rule 2903 (dpkg removed), rule 2932 (level 7, "New Yum package installed"), rule 2933 (Yum package updated). A binary modified minutes after a matching package update is probably routine; the same change with no package activity is suspicious.
  3. Correlate with account events: rule 5902 (level 8, "New user added to the system"), rule 5901 (level 8, "New group added to the system"), rule 5904 (level 8, "Information from the user was changed"), rule 2833 (level 8, "Root's crontab entry changed").
  4. Who did it: use who-data if present; otherwise look for logins/sudo on the agent around the change (e.g. rule 5402 (level 3, "Successful sudo to ROOT executed")).
  5. Process context: if a process is implicated, hand off to investigation (it holds get_agent_processes / get_agent_ports) unless you are investigation.
  6. Hashes: send sha256_after of new/modified executables to threat-intel for reputation.
  7. Deletions: bulk rule 553 on data directories plus new files with unusual extensions is a ransomware pattern — escalate immediately (see ir-playbook-ransomware).

Noise

Log rotation, package managers, configuration management (Ansible/Puppet/Chef runs at fixed times), antivirus definition updates, and editors creating temp files. Suggest a scoped level-0 child rule via detection-engineer rather than disabling FIM on a path.

Output

  • add_entities: file paths (type file), hashes (type hash), user and process from who-data.
  • link_mitre for the persistence/tampering technique you can support with evidence.
  • add_finding: what changed, when, who (or "who-data not enabled"), routine-vs-suspicious verdict with the evidence (package event present/absent), and standard refs such as MITRE-ATTACK:T1547.001, PCI-DSS-4:11.5, CIS-v8.1:3.

Frequently asked questions

What does the Wazuh Fim Investigation AI skill do?

Investigate Wazuh File Integrity Monitoring (syscheck) alerts — file and registry add/modify/delete events, checksums, permissions and who-data — separate tampering from routine change and pivot to processes and users; use for any syscheck alert or suspected persistence/tampering.

Why use Wazuh Fim Investigation on TypingMind?

Because you install it once and use it with any model. Wazuh Fim Investigation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wazuh Fim Investigation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gensecaihq/Wazuh-Autopilot/tree/main/backend/app/skills/wazuh-fim-investigation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Wazuh Fim Investigation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wazuh Fim Investigation?

As many as you like. As long as a model supports skills, you can use Wazuh Fim Investigation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wazuh Fim Investigation AI skill free?

Yes. It is published on GitHub by gensecaihq under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇