Identity Compromise

Organization

gensecaihq

identity-compromise

Investigate suspected account compromise — brute force followed by success, impossible travel, privilege escalation and lateral movement across Linux and Windows; use when a user account appears in suspicious authentication activity.

Overview

Publisher	gensecaihq
Repository	`Wazuh-Autopilot`
Skill name	`identity-compromise`
Stars	61
Forks	15
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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 Identity Compromise AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/gensecaihq/Wazuh-Autopilot/tree/main/backend/app/skills/identity-compromise
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/gensecaihq/Wazuh-Autopilot/tree/main/backend/app/skills/identity-compromise

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/identity-compromise .claude/skills/identity-compromise

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Identity Compromise 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 Identity Compromise 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 Identity Compromise 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.

Identity Compromise Investigation

Accounts are the most common path to impact. Decide whether an account is compromised, how far it was used, and what containment is justified.

Key events and the Wazuh rules that surface them

Rule numbers are from the stock Wazuh 4.14 ruleset. Many Windows events are only alerted on when the channel is collected and not filtered. If there's no rule, search the raw event with search_security_events (field data.win.system.eventID). Load wazuh-windows-sysmon for Windows field paths.

Platform	Event	Wazuh rules	Meaning
Windows	Event ID 4624	rule 60106 (level 3)	successful logon; check `data.win.eventdata.logonType`: 2 interactive, 3 network, 10 RemoteInteractive/RDP
Windows	Event ID 4625	rules 60105, 60122 (level 5); burst → rule 60204 (level 10)	failed logon; `subStatus` separates bad password from unknown user
Windows	Event ID 4648	none (search raw events)	logon with explicit credentials (runas, lateral tools)
Windows	Event ID 4672	rule 67028 (level 3)	special privileges assigned: admin-equivalent logon. Low level, high meaning for non-admins
Windows	Event ID 4720, Event ID 4722	rule 60109 (level 8)	account created / enabled
Windows	Event ID 4738	rule 60110 (level 8)	account changed
Windows	Event ID 4728, Event ID 4732, Event ID 4756	rules 60141, 60144, 60151 (level 5); rule 60154 Administrators group changed (level 12)	member added to security-enabled global / local / universal group
Windows	Event ID 4740 lockout	rule 60115 (level 9)	account locked out after multiple failures
Windows	Event ID 4768, Event ID 4771	none stock (search raw events)	Kerberos TGT request / pre-auth failure: spraying against a DC
Linux	sshd failure	rules 5716, 5760 (level 5); rule 5710 non-existent user (level 5)	single failures
Linux	sshd burst	rules 5712, 5720, 5763 (level 10); rule 5758 max attempts exceeded (level 8)	composite brute-force rules
Linux	sshd success	rule 5715 (level 3)	`Accepted password` / `publickey`
Linux	sudo	rule 5402 to root (level 3), rule 5401 failed (level 5), rule 5403 first time for user (level 4)	privilege use
Linux	PAM	rule 5503 login failed (level 5), rule 5551 multiple failures (level 10)	console / other PAM services
Linux	account changes	rule 5902 new user (level 8), rule 5904 user information changed (level 8)	useradd / usermod

Procedure

List all auth events for the user over 7 days (search_security_events(query="<user>")), and aggregate by source IP and host (get_alerts_aggregated).
Establish baseline: usual source IPs, hosts, hours, logon types.
Test each hypothesis below; record which are supported.
Determine scope: every host the account touched after the suspected compromise time.

Hypotheses and indicators

Pattern	Indicators	ATT&CK
Brute force → success	rule 60204 or rules 5712, 5763 then rule 60106 or rule 5715 from the same source	T1110 → T1078
Password spraying	one source, many users, few attempts each	T1110.003
Impossible travel	successful logons from locations whose distance/time implies > ~900 km/h	T1078
New source / off-hours	success from never-seen IP/ASN or outside baseline hours	T1078
Privilege escalation	rule 67028 for a non-admin, group adds (rules 60141, 60144, 60154), rule 5402 by an unusual user	T1078.002/.003, T1098
Lateral movement	same account, new hosts in short time; logon type 3/10 chains; SSH hops	T1021 (.001 RDP, .002 SMB, .004 SSH)
Persistence via account	new account created by the suspect account (rules 60109, 5902), SSH key added (FIM on `authorized_keys`, see `wazuh-fim-investigation`)	T1136, T1098.004

Verdict

Compromised — success from attacker-controlled source, or malicious actions by the account. Confidence ≥ 0.8.
Targeted, not compromised — failures only, no success. Recommend blocking the source, not disabling the user.
Inconclusive — anomalies without malicious actions; recommend user verification.

Recommend disable_user (proposed by response-planner) only with evidence of successful malicious use. Service accounts and break-glass accounts: flag the business impact explicitly; prefer blocking the source or isolating the host first.

Output

add_entities (user as victim; source IPs as attacker; hosts touched).
link_mitre for supported techniques.
update_case severity/confidence.
add_finding titled Identity assessment: <user> with baseline, hypotheses table (supported / not supported + evidence), hosts in scope, verdict, recommended containment. standard_refs: NIST-800-61r3, CIS-v8.1:5 (Account Management), CIS-v8.1:6 (Access Control Management).

Frequently asked questions

What does the Identity Compromise AI skill do?

Why use Identity Compromise on TypingMind?

Because you install it once and use it with any model. Identity Compromise 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 Identity Compromise in TypingMind?

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

Which AI models can use Identity Compromise?

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 Identity Compromise?

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

Is the Identity Compromise 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

Product Capability

affaan-m

CommunityPopular

Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service…

Django Patterns

Patrones de arquitectura Django, diseño de API REST con DRF, buenas prácticas de ORM, caché, señales, middleware y aplicaciones Django de nivel producción.

Quarkus Patterns

Patrones de arquitectura Quarkus 3.x LTS con Camel para mensajería, diseño de API RESTful, servicios CDI, acceso a datos con Panache y procesamiento asíncrono.

Quarkus Security

Buenas prácticas de seguridad en Quarkus para autenticación, autorización, JWT/OIDC, RBAC, validación de entrada, CSRF, gestión de secretos y seguridad de dependencias.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Identity Compromise Investigation

Key events and the Wazuh rules that surface them

Procedure

Hypotheses and indicators

Verdict

Output

Frequently asked questions

Related AI Skills

Set up your own AI workspace now