Anthropic Releases Dataset of 817 Cybersecurity Skills for AI Agents
mukul975 · github · 2026-08-17
- Dataset: Contains 817 structured cybersecurity skills mapped to 6 frameworks including MITRE ATT&CK and NIST CSF 2.0.
- Compatibility: Adheres to agentskills.io standard and works with 20+ platforms like Claude Code, GitHub Copilot, and Cursor.
- Use Cases: Covers 29 security domains to enhance AI agents in tasks like cloud security, penetration testing, and threat intelligence.
More from coding & agent
- Mediocre Agent Data Science Output? Needs Custom Skills — daveholtz · 2026-08-17
- AI Agents Fail to Respect Field-Specific Norms in Academic Research — daveholtz · 2026-08-17
- OKF vs wikillm: How to choose for agent context? — frakc · 2026-08-17
- Bad code means bad agents: Software fundamentals matter more than ever — mattpocockuk · 2026-08-17
- How to gate Agent actions in production environments? — Excellent-Park-1160 · 2026-08-17
- Open Source UnFlow: Graph-based ML Experimentation Tool — ha2emnomer · 2026-08-17