Rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Complete security audit of pending changes on the current branch.
Runs a security-focused review on the current branch's diff. Flags OWASP-style issues (injection, auth, crypto, access control), surfaces insecure deserialization, hardcoded secrets, and dependency issues.
git clone --depth 1 https://github.com/anthropics/claude-code-security-review.git ~/.claude/skills/security-review
Restart Claude Code afterwards. See the README for skill-specific setup.
Using Codex CLI? Copy the same folder to ~/.codex/skills/security-review instead.
security reviewsecurity auditcheck vulnerabilitiesRuns a security-focused review on the current branch's diff. Flags OWASP-style issues (injection, auth, crypto, access control), surfaces insecure deserialization, hardcoded secrets, and dependency issues.
Clone it into your personal skills folder: git clone --depth 1 https://github.com/anthropics/claude-code-security-review.git ~/.claude/skills/security-review — then restart Claude Code.
Security Review is open source on GitHub (0 stars at last check) and published by Anthropic.
Browse other security skills in the Security category of this directory.