Summary
This is an LLM-powered pentesting agent that won 4th place and achieved a unique "AK" (all challenges solved) at Tencent's Cloud Hackathon intelligent penetration challenge. It's built on a ReAct loop where the AI reasons about targets, selects tools like nmap and sqlmap, executes them, and interprets results to chain together multi-step exploits. The repo shows it's still being organized and not fully open-sourced yet, but the architecture is documented in their competition writeup. If you're exploring autonomous security testing or CTF automation, this is an interesting reference implementation from a team that clearly knows what they're doing. Just be aware the codebase is in flux.
Install to Claude Code
npx -y skills add aradotso/trending-skills --skill cairn-ai-pentest --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
