agentleFS
Wang200935Wang200935/security-agent-skills/AGENTS.md

security-agent-skills

AGENTS.md4 starsChanged 3 months agoMITView on GitHub

This project contains 79 security skills organized into 9 domains under skills/.

The file

Files
AGENTS.md

Security Agent Skills — Project Instructions

Skill Loading

This project contains 79 security skills organized into 9 domains under skills/.

Load Order

  1. Load skills/security-orchestrator/SKILL.md only for cross-domain routing
  2. The orchestrator analyzes user intent and loads the right skill(s)
  3. Multiple skills can load in parallel for speed

Skill Categories

  • skills/recon/ — OSINT, reconnaissance, dark web research
  • skills/web-pentest/ — Web app testing, API security, WAF bypass
  • skills/network-pentest/ — Network scanning, AD attacks, lateral movement
  • skills/exploit-dev/ — Zero-day hunting, fuzzing, kernel exploitation, crypto
  • skills/reverse-engineering/ — Binary analysis, firmware, Ghidra/IDA/radare2
  • skills/ctf/ — CTF challenges across all categories
  • skills/post-exploitation/ — Privilege escalation, persistence, reporting
  • skills/cloud-security/ — AI/MCP security, code audit, modern attack surfaces
  • skills/hardware-iot/ — UART/JTAG/SPI, firmware, SDR, Flipper Zero, ESP32

Rules Library

Shared knowledge in rules/security-rules.md is loaded across skills for attack payloads, techniques, WAF bypass patterns, hunting rules, and common mistakes.

Authorized Use Only

These skills are for authorized security testing only. The user is responsible for obtaining proper authorization before testing any system.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.