Security Guidance (security-review)
Anthropic plugin that reviews each code change for vulnerabilities across three checkpoints and instructs Claude to fix them.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Security Guidance (security-review), 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
The security-guidance plugin from Anthropic reviews each change Claude makes for common vulnerabilities and instructs Claude to fix them in the same session. It operates across three checkpoints, the first being a fast deterministic pattern match on every file edit (a hook) that flags dangerous constructs like eval(), new Function(), os.system(), child_process.exec(), pickle deserialization, and DOM injection. It covers 25 high-risk vulnerability types.
Key features and capabilities
- Deterministic per-edit pattern-match hook
- Three-layer review pipeline
- Flags eval/exec/pickle/DOM-injection sinks
- Covers 25 high-risk vulnerability types
Use cases
- Shift-left vulnerability detection while coding
- Auto-fixing insecure code in the same session