Skip to main content
skill CX Codex

h-pentest-ai-platform — Claude Code skill: what it does

h-pentest-ai-platform — a skill that walks an agent through standing up H-Pentest: five LLM roles plan the test, suggest payloads, scan with Nuclei and write up what they find.

no license 248 installs ★ 13 updated 2026-10-09

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add reason-machines/security-skills --skill h-pentest-ai-platform -a claude-code
Open on GitHub

What h-pentest-ai-platform does

The skill teaches your agent to stand up and drive H-Pentest, a pentest platform split across five LLM roles. A meta supervisor calls time on the run, a strategic one redraws the plan each round, a worker follows a reason-act-observe loop, a payload role offers vectors every 3 rounds, and a report role turns the transcript into attack paths. Behind them sits a knowledge base of 52+ attack documents covering IDOR, SQL injection, XSS, SSRF, XXE and file upload, fetched through retrieval.

Docker Compose brings the whole thing up, or you can run the pieces yourself: the Python backend needs pip install -r requirements.txt and python init_db.py, the frontend runs on npm. The API listens on http://localhost:8000 with docs at /docs, the UI on http://localhost:5173. Progress arrives over WebSocket, and a message to the intervention endpoint nudges a running agent. Python code runs inside a Docker sandbox alongside Nuclei and a directory scanner.

Both keys live in config.json: openai.api_key for the models, dashscope.api_key for embeddings. Knowledge-base search depends on the second one. There are two modes, ctf and realworld, and the meta supervisor takes the choice into account. Sandbox limits sit in the same file: execute_python gets 30 seconds and 512m of memory, Nuclei runs at critical, high and medium severity.

What it helps with

  • bring the platform up from a Compose file
  • create a ctf task against a target URL
  • look up a bypass technique in the attack knowledge base
  • wire Nuclei into the agent and filter findings by severity
  • step into a running agent and point it at another endpoint

Example prompts for the agent

  • Set up H-Pentest with Docker Compose and tell me which keys go into config.json.
  • Create a ctf task for http://target-ctf.example.com with 25 rounds and follow it over WebSocket.
  • Run a realworld scan on the staging app and send the worker to the /api/admin endpoint.

How to install h-pentest-ai-platform

1Skills CLI (Vercel)

npx skills add reason-machines/security-skills --skill h-pentest-ai-platform -a claude-code

2Manually: put the files in place

~/.claude/skills/h-pentest-ai-platform/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/h-pentest-ai-platform/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about h-pentest-ai-platform

How do I install h-pentest-ai-platform in Claude Code?

Run npx skills add reason-machines/security-skills --skill h-pentest-ai-platform -a claude-code. The skill file lands at ~/.claude/skills/h-pentest-ai-platform/SKILL.md.

What does h-pentest-ai-platform do?

It gets your agent through the H-Pentest setup and then through real pentest runs: supervisor and worker roles, attack knowledge lookup, Python in a sandbox, Nuclei scans and a closing report of what was found.

Do I need my own API keys to run it?

Yes, two of them in config.json: openai.api_key for the models and dashscope.api_key for embeddings. The same file holds base_url and the model name, set separately for the main model and the supervisor.

Similar skills

All skills for Security →

From the same set129

The whole set →
gandalf-llm-pentester gandalf-llm-pentester automates security testing of prompt defenses across 7 challenge tiers on Lakera Gandalf. Useful when checking how language models resist injection attempts. CX Codex +1 252installs awesome-pentest-tools-catalog awesome-pentest-tools-catalog is a Claude Code skill for finding penetration testing and red team tools by workflow stage and MITRE ATT&CK. CX Codex +1 251installs dalonso-security-repo dalonso-security-repo brings Microsoft Security hunting material into your agent: KQL queries, Sentinel workbooks and Jupyter notebooks for incident work. CX Codex +1 251installs awesome-ai-security-reference The awesome-ai-security-reference skill points to learning resources and tools for AI security, from prompt injection to privacy attacks. Use it to explore a topic or find ways to test a model. CX Codex +1 248installs ai2pentesttool-installer ai2pentesttool-installer — a skill that drives a Python installer for pentest and security tools: it reports what is already on the machine, adds the rest, and retries a step that failed. CX Codex +1 246installs pentest-ai-killer-automation pentest-ai-killer-automation wires your assistant to the Pentest AI Killer server, which exposes 69+ security tools such as nmap, nuclei and sqlmap over MCP and a REST API. CX Codex +1 244installs symfony-security-auditor symfony-security-auditor audits Symfony codebases for business logic flaws and authorization bugs. Uses dual-agent LLM analysis to catch issues missed by static scanners. CX Codex +1 239installs android-app-pentest-environment android-app-pentest-environment — a skill that builds an Android pentest bench for you: rooted emulator, Magisk, LSPosed and captured app traffic. CX Codex +1 236installs

Project sponsors

Companies that keep this analytics open