security-guidance
Security review plugin: pattern warnings on edits, LLM diff review on Stop, and an agentic commit reviewer for injection/XSS/SSRF/secrets.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for security-guidance, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official security plugin for Claude Code. It adds a PostToolUse hook that pattern-matches edits for risky code, a Stop hook that runs an LLM-powered review of the session diff, and an agentic commit reviewer that flags command injection, XSS, SSRF, hardcoded secrets and 25+ other vulnerability classes. Surface is entirely hooks plus a review agent that runs shell/LLM on edit and stop events.
Key features and capabilities
- PostToolUse pattern-based security warnings on file edits
- LLM-powered diff review triggered on the Stop hook
- Agentic commit reviewer covering 25+ vulnerability classes
- Detects injection, XSS, SSRF, and hardcoded secrets
Use cases
- Catch insecure patterns in Claude-generated code before commit
- Automated security gate on every session's diff