A list of AI security skills (WIP).
CAUTION!! - I HAVE NOT MANUALLY VERIFIED ALL OF THESE. RUNNING SKILLS FROM OTHERS CAN COMPROMISE YOUR MACHINE. BE CAREFUL.
Please make an issue to add yours. Contributions are welcome.
Come chat about AI hacking agents in the AI Hacking Discord https://discord.gg/9AJnkNe6RE
https://github.com/trailofbits/skills - A Claude Code plugin marketplace from Trail of Bits providing skills to enhance AI-assisted security analysis, testing, and development workflows. Codex can load this marketplace through its Claude marketplace compatibility.
https://github.com/Netflix-Skunkworks/railguard-skill - Railguard is an experiment in LLM-driven static security analysis. This is a repository emulating the different approaches for quick evaluation leveraging Claude Code agent skills to scan source code repositories for security vulnerabilities; no runtime execution, no dynamic testing, pure read-and-reason.
https://github.com/Mindgard/ai-ide-skills - Claude Code skills plugin for security testing AI-assisted IDEs and coding agents. 8 skills covering 25 vulnerability patterns across 4 classes (code execution, prompt injection, data exfiltration, trust persistence), with 5 canonical attack chain templates. Supports both black-box assessment (documentation analysis, runtime observation, payload testing) and white-box assessment (source code auditing with semgrep/CodeQL queries, static analysis templates). Each skill includes step-by-step methodology, copy-pasteable payloads, and known vulnerability references.
https://github.com/ghostsecurity/skills - Plugin marketplace repository for Ghost Security's AI-native application security skills for Claude Code.
https://github.com/semgrep/skills - A collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities. This should be considered beta-level software; it's primarily generated by transforming open-source Semgrep rules into skill format.
https://github.com/SnailSploit/Claude-Red - Offensive security skills for Claude — drop-in SKILL.md files that turn Claude into a context-aware red team operator.
https://github.com/Eyadkelleh/awesome-claude-skills-security - A curated collection of security testing resources packaged as agent skills, available on skills.sh
https://github.com/MuzamilAdigun/Claude-Code-Security-Audit - 10 security audit slash commands for Claude Code, covering 9 major compliance frameworks. Designed for vibe coders and developers who want to identify and fix security vulnerabilities in their projects.
https://github.com/Masriyan/Claude-Code-CyberSecurity-Skill - A comprehensive collection of 15 Claude Code Skills for cybersecurity professionals ,covering offensive security, defensive operations, reverse engineering, threat hunting, CSOC automation, and more.
https://github.com/eth0izzle/security-skills - A plugin marketplace of Claude Code skills that automate security operations.
https://github.com/UnitOneAI/SecuritySkills - Open-source security skills for AI coding agents. Grounded in OWASP, NIST, MITRE ATT&CK, CIS. Works with Claude Code, Gemini CLI, Cursor, Codex CLI, OpenClaw, Kiro.
https://github.com/DeepBitsTechnology/claude-plugins - The Plugin equips Claude Code with advanced binary analysis capabilities for tasks such as incident response, malware investigation, and vulnerability assessment. It connects to both cloud-based analysis platforms and local tools via MCP, enabling seamless hybrid workflows. With features including local Windows system scanning, browser hijacking detection, registry and network monitoring, suspicious file analysis, and remote binary analysis through tools like Ghidra, Qilin, and angr, the plugin transforms Claude Code into a powerful AI-assisted workspace for comprehensive system and binary security analysis.
https://github.com/wrsmith108/claude-skill-security-auditor - A Claude Code skill for running structured security audits with actionable remediation plans.
https://github.com/tanweai/wooyun-legacy - (Not in English) https://x.com/blackorbird/status/2015459116224008532. WooYun Legacy is a Claude Code plugin built on 22,132 business logic vulnerability cases collected by WooYun (2010–2016). It injects real company case references, quantitative statistics, and data-driven test prioritization into Claude's security testing output.
https://github.com/GabrielYMC/security-audit - (Not in English) AI agent skill for pre-deploy security audits on vibe-coded web projects. 55 rules, 8 categories, evidence-based findings. Works with Claude Code / Claude.ai.
https://github.com/netresearch/security-audit-skill - Agent Skill for PHP security audits - OWASP patterns, vulnerability detection | Claude Code compatible
https://github.com/akdenizemirhan/agent-rock - Deep security audit skill for Claude Code
https://github.com/behever/app-security-audit - AI agent skill for comprehensive security auditing of web apps, Supabase, databases, mobile apps, and APIs. Checks RLS policies, XSS/CSRF, exposed secrets, auth issues, OWASP Top 10, and more.
https://github.com/Netropolitan/Claude-Security-Audit - Claude Code skill that spawns 6 agents for security and accessibility auditing — two auditors scan in parallel, findings presented by severity for approval, fixes planned with blast radius, applied one-at-a-time with checkpoints, and independently verified. Covers 14 security categories and WCAG 2.2 AA.
https://github.com/yoanbernabeu/supabase-pentest-skills - 24 AI Agent Skills for professional security auditing of Supabase applications. Detection, key extraction, RLS testing, storage audit, IDOR detection, and comprehensive reporting. Works with Claude Code, Cursor, Windsurf, and 30+ AI agents.
https://github.com/mukul975/Anthropic-Cybersecurity-Skills - 754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 26 security domains · Apache 2.0
https://github.com/BehiSecc/bugSkills - Convert your HackerOne reports into reusable AI skills.
https://github.com/ljagiello/ctf-skills - Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more
https://github.com/elastic/agent-skills - Elastic Agent Skills — built by the people who built Elastic — deliver native platform expertise directly to your AI coding agent. This is the official Agent Skills library, compatible with agentic IDEs such as Cursor, GitHub Copilot, Windsurf, Gemini CLI, and more. Skills follow the Agent Skills open standard.
https://github.com/Security-Phoenix-demo/security-skills-claude-code - This repository is a curated collection of skills, plugins, and automation pipelines designed for Claude Code — Anthropic's CLI for AI-assisted software engineering. It was built by the engineering and security engineering teams at Phoenix Security and released as open source so that security professionals, DevSecOps engineers, AppSec teams
https://github.com/pashov/ai-web3-security - web3 security skills list.
https://github.com/elementalsouls/Claude-BugHunter - A Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.
https://github.com/Gabson0x/bountyforge - All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, and submission-ready reports for HackerOne, Bugcrowd, Intigriti & Immunefi.
https://github.com/NVIDIA/SkillSpector - Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills.
https://github.com/cisco-ai-defense/skill-scanner - A best-effort security scanner for AI Agent Skills that detects prompt injection, data exfiltration, and malicious code patterns. Combines pattern-based detection (YAML + YARA), LLM-as-a-judge, and behavioral dataflow analysis to maximize detection coverage of probable threats while minimizing false positives.
https://github.com/Repello-AI/skill-check - SkillCheck by Repello AI: free hosted scanner that audits MCP skills and AI agent tools for prompt injection, data exfiltration, and security issues. Live at https://skills.repello.ai/.
https://github.com/openclaw/clawhub/blob/c3c885ec10161ad35fbe78678ccc3f8c34e03ffd/convex/lib/securityPrompt.ts - ClawHub's malicious skill detector.
https://github.com/aliksir/claude-code-skill-security-check - Security audit skill for Claude Code community skills. Scans for prompt injection, data exfiltration, permission bypass, dangerous commands, and supply chain risks.
https://github.com/anthropics/claude-code-security-review - prompts and scripts for Claude Code security review workflows that produce structured findings and fixes.
https://github.com/trailofbits/skills-curated - reviewed and approved Trail of Bits Claude Code plugins.
https://github.com/YARAHQ/yara-rule-skill - LLM agent skill for YARA rule authoring, review, and optimization.
https://github.com/badsectorlabs/ludus-skills - AI agent skills for Ludus cyber ranges.
https://github.com/blacklanternsecurity/red-run - security assessment toolkit for Claude Code.
https://github.com/atredispartners/llmchainhunter - Claude Code design plan and runbook for Java deserialization gadget-chain hunting.
https://github.com/mcpeak/cursor-security-automation - Cursor security automations and custom security MCP for agentic security review, vulnerability hunting, dependency patching, and invariant monitoring.
https://github.com/prompt-security/clawsec - installable security skill suite for OpenClaw agents.
https://github.com/vulhunt-re/skills - reverse-engineering and vulnerability-hunting skills powered by VulHunt MCP tools.
https://github.com/BrownFineSecurity/iothackbot - IoT security toolkit combining Python CLI tools and Claude Code skills for discovery, firmware analysis, and testing.
https://github.com/matank001/cursor-security-rules - Cursor security rules for secure development workflows and AI agent usage.
https://github.com/wiz-sec-public/secure-rules-files - baseline rules files for safer AI coding assistants.
https://github.com/vulhunt-re/rules - companion community rules repo for VulHunt workflows.
https://github.com/project-codeguard/rules - model-agnostic AI security ruleset for policy enforcement and unsafe tool detection.
https://github.com/ComposioHQ/awesome-claude-skills - curated Claude Skills collection with a Security & Systems section.
https://github.com/tsale/awesome-dfir-skills - community library of DFIR skills, prompts, workflows, and helpers.
https://github.com/sickn33/antigravity-awesome-skills https://www.skills.sh/
https://github.com/transilienceai/communitytools https://github.com/vinayaklatthe/microsoft-security-skills https://github.com/forefy/.context
https://github.com/google/mantis