Assess Agent & MCP security Defense not yet reviewed
skill-scanner
Cisco's Skill Scanner statically and behaviorally scans AI Agent Skills (Codex, Cursor, and lenient Claude Code formats) for prompt injection, data exfiltration, and malicious code, with an optional LLM judge. It is aimed at teams vetting agent skills before installing or committing them.
Promising or important to understand; evaluate, don't depend on it yet.
Facts
- Repository
- cisco-ai-defense/skill-scanner
- Homepage
- github.com
- Listed via
- Awesome list
- First seen
- 2026-11-09
- License
- open source
- Stars
- 2,709
- Last commit
- 2026-11-06
- Checked
- 2026-11-09
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.