Ir Playbook Bruteforce

Organization

gensecaihq

ir-playbook-bruteforce

Incident-response playbook (PB-001) for brute-force, password-spraying and credential-stuffing attacks against SSH, PAM, Windows logon and web logins; use when Wazuh raises authentication-failure bursts (rule group authentication_failures, e.g. rules 5712, 5763, 60204) or a failure burst followed by a success (rule 40112).

Overview

Publisher	gensecaihq
Repository	`Wazuh-Autopilot`
Skill name	`ir-playbook-bruteforce`
Stars	61
Forks	15
Bundled files	1
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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by gensecaihq on GitHub. Read the source before you install it.

Installation

Install the Ir Playbook Bruteforce 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/ir-playbook-bruteforce
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/ir-playbook-bruteforce

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/ir-playbook-bruteforce .claude/skills/ir-playbook-bruteforce

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

Use it in TypingMind

Enable Ir Playbook Bruteforce 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 Ir Playbook Bruteforce 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 Ir Playbook Bruteforce 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.

IR Playbook — Brute Force (PB-001)

Semi-automated: the swarm detects, investigates and proposes; the autonomy policy and the approvals queue decide what executes. Default severity high, critical once a login succeeds. MITRE ATT&CK T1110 (.001 Password Guessing, .003 Password Spraying, .004 Credential Stuffing). Rule IDs below are from the stock Wazuh 4.14 ruleset; levels are the official ones. Full procedure: references/playbook.md.

1. Detection signals

Signal	Wazuh rules (level)	Notes
SSH single failures	rules 5710 (L5, non-existent user), 5716 (L5), 5760 (L5)	group `authentication_failed`
SSH brute force (composite)	rules 5712 (L10, non-existent users), 5763 (L10, auth failed), 5720 (L10), 5758 (L8, max attempts exceeded)	group `authentication_failures`
PAM / syslog repeated failures	rules 5503 (L5), 5551 (L10), 2502 (L10)	Linux console/su/other PAM services
Windows logon failures (Event ID 4625)	rules 60122 (L5), 60204 (L10, multiple failures)	eventchannel, group `windows_security`
Windows account lockout (Event ID 4740)	rule 60115 (L9)	lockouts across many accounts = spraying
Any source, many failures (cross-decoder)	rule 40111 (L10)	frequency rule on group `authentication_failed`, same source IP
Failures followed by a success	rule 40112 (L12)	same source IP within 240 s — escalate to critical
Success events to check	rules 5715 (L3, sshd success), 60106 (L3, Event ID 4624)	correlate with the failing source
Web / CMS logins	rule 31510 (L8, WordPress/Joomla brute force); rule 31151 (L10, many HTTP 400s)	other web apps need custom rules

Stock gaps (create as custom rules, range 100000–120000):

Password spraying (one source, ≥10 distinct accounts, few attempts each) — e.g. custom rule 100210: <rule id="100210" level="10" frequency="10" timeframe="1800"><if_matched_group>authentication_failed</if_matched_group><same_source_ip /><different_field>dstuser</different_field>…
Credential stuffing (one account, many sources) — custom rule 100211 using <same_field>dstuser</same_field> with <different_srcip />.
VPN / cloud / API logins not covered by an installed decoder.
Validate custom rule syntax against your manager version (wazuh-logtest) before deploying.

2. Triage / investigation (investigation agent)

Pull context: get_wazuh_alerts (agent_id, rule_groups: ["authentication_failed","authentication_failures"], timestamp_start: "now-6h", compact: true) and search_security_events (query: "authentication", srcip: <ip>, time_range: "24h") across the fleet. search_cases on the source IP before creating anything; case creation belongs to triage.
Answer:
- Single source or distributed? Internal or external? External IPs → hand off to threat-intel for reputation.
- One account (guessing) or many (spraying)? Privileged accounts targeted (root, Administrator, svc_*)?
- Did any attempt succeed? Look for rule 40112, or rules 5715, 60106 from the same source after the failures.
- Internet-facing target? (get_wazuh_agents → groups, IP)
add_entities (source IP = attacker, host = victim with agent_id in enrichment, targeted users = victim), link_mitre T1110.x, update_case severity (failures only → high; success → critical).
Only if a login succeeded or the source is internal: get_agent_processes / get_agent_ports on the target (new shells, reverse connections, miners); check post-login activity — sudo to root (rule 5402, L3), new users (rule 5902, L8), root crontab changes (rule 2833, L8), SSH keys added (FIM on authorized_keys, rules 550, 554). Internal source → hand off to lateral-movement analysis.
add_finding with the evidence and a containment recommendation to response-planner (target IP, agent_id, affected users, whether a login succeeded).

3. Response (response-planner)

Propose, never execute. Include confidence and a rationale with rollback in every call. Check current state first with wazuh_check_blocked_ip so you don't propose a duplicate block.

Situation	Proposal
External source, failures only	`propose_action(type="block_ip", target=<ip>, params={"ip_address": <ip>, "agent_id": <target agent>})` — low risk, reversible (D3-ITF)
Same source hitting many hosts	`block_ip` with `params={"ip_address": <ip>, "all_agents": true}` — say "fleet-wide" in the rationale
Linux SSH target, per-host deny	`propose_action(type="host_deny", params={"agent_id": <id>, "ip_address": <ip>})`
Firewall drop on one host	`propose_action(type="firewall_drop", params={"agent_id": <id>, "ip_address": <ip>})`
Login succeeded with an attacked account	`propose_action(type="disable_user", target=<user>, params={"agent_id": <id>, "username": <user>})` (D3-AL, high risk → supervised)
Hands-on-keyboard after login	`propose_action(type="isolate_host", target=<id>, params={"agent_id": <id>})` (D3-NI, high risk)
Malicious process started post-login	`propose_action(type="kill_process", params={"agent_id": <id>, "process_id": <pid>})` after evidence capture

Order: block the source first; disable accounts only with evidence of success; isolate only with evidence of compromise. Protected hosts/users are refused by policy. Rate limiting, MFA and password resets are human follow-ups — record them with add_finding.

4. Eradication and recovery

Reset credentials for any account that authenticated from the attacking source (human task).
Remove attacker SSH keys, cron jobs and new accounts; confirm with FIM alerts and get_agent_processes.
Harden: key-only SSH, lockout policy, MFA on remote access, no internet-facing RDP.
Monitor the source and targeted accounts for 24–72 h; close when quiet.

5. Verification

The responder verifies executed actions (wazuh_check_blocked_ip with ip_address/agent_id, wazuh_check_user_status with agent_id/username) and recommends rollback if a legitimate service is hit.

6. Evidence and records

add_finding per stage with standard_refs, e.g. NIST-800-61r3:Respond, MITRE-ATTACK:T1110.003, SANS-PICERL:Containment, PCI-DSS-4:Req 10.
Record source IPs + reputation, targeted accounts, attempt counts and window, first/last seen, success yes/no, and actions proposed/approved/verified.
Detection gap (e.g. spraying below threshold)? Hand off to detection-engineer with the custom rule sketch above.
Critical cases: hand off to reporting for the incident report.

Escalation

Condition	Escalate to
Successful login on a privileged/production account (rule 40112)	SOC lead + IR lead (human), severity critical
Distributed attack from > 50 sources	Network team (edge rate limiting)
Internal source	`ir-playbook-lateral-movement`

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/playbook.md72 KB

Frequently asked questions

What does the Ir Playbook Bruteforce AI skill do?

Why use Ir Playbook Bruteforce on TypingMind?

Because you install it once and use it with any model. Ir Playbook Bruteforce 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 Ir Playbook Bruteforce in TypingMind?

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

Which AI models can use Ir Playbook Bruteforce?

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 Ir Playbook Bruteforce?

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

Is the Ir Playbook Bruteforce 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

Huggingface Hub

NousResearch

OrganizationPopular

HuggingFace hf CLI: search/download/upload models, datasets.

Pinecone

Managed vector DB for production RAG and search.

Qdrant

Vector search engine for production RAG systems.

Tensorrt Llm

High-throughput LLM inference on NVIDIA GPUs.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

IR Playbook — Brute Force (PB-001)

1. Detection signals

2. Triage / investigation (investigation agent)

3. Response (response-planner)

4. Eradication and recovery

5. Verification

6. Evidence and records

Escalation

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now