Overview
Anthropic Cybersecurity Skills provides 754 structured cybersecurity skills for AI agents, mapped to 5 major security frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, and NIST AI RMF. It works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, and 20+ platforms.
Key Features
- 754 structured cybersecurity skills across 26 security domains
- Mapped to MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, and NIST AI RMF
- Compatible with Claude Code, Copilot, Codex CLI, Cursor, Gemini CLI, and 20+ platforms
- agentskills.io standard format
Use Cases
- Automated security assessment and penetration testing with AI agents
- Threat intelligence analysis and incident response
- Security-aware code review and DevSecOps automation
Technical Details
- Apache 2.0 licensed, covering 26 security domains
- Structured in agentskills.io standard format
- Covers OSINT, malware analysis, cloud security, threat hunting, and more