Anthropic-Cybersecurity-Skills
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0
- stars
- 32,795
- 30-day movement
- +28294/day
- Related entries
- 120
- Connections
- 2
A repository of 817 structured cybersecurity skills for AI agents, organized across 29 security domains and mapped to six frameworks including MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF, and MITRE F3. It follows the agentskills.io standard and ships an AGENTS.md file, with compatibility claimed for Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, and 20+ other platforms.
You want a ready-made, framework-mapped library of security skills to give AI coding agents cybersecurity capabilities without writing them yourself.
Use it to
- Equip coding agents with cybersecurity skills
- Map agent capabilities to MITRE ATT&CK and NIST CSF
- Support red-team and penetration-testing agent workflows
- Automate incident-response and threat-hunting tasks
- Standardize security skills across multiple agent platforms
For Security engineers and agent developers
- Role
- agent-app
- Language
- Python
- Licence
- Apache-2.0
- Forks
- 3,960
- Open issues
- 21
- Last push
- 2026-08-31
- Latest release
- v1.0.0 · 2026-03-11
- Skills shipped
- 818