Review code for security, correctness, performance, maintainability and testing gaps.
Security Skills for Claude Code, Codex & AI Agents
These skills let an agent review code for vulnerabilities, run penetration-testing workflows against a web app or API, and dig into compiled binaries. The page brings together Strix testing, hardening, dependency review, and reverse engineering.
26 skillsSub-topics
Explore Security skills
5 skillsPonytail: Codebase Audit
Produce a ranked repository audit covering bugs, risky untested code, slow paths and code bloat.
Ponytail: Code Review
Review a change and its connected code for correctness, safety, performance and unnecessary complexity.
Find security vulnerabilities in a codebase or repository with Strix — a white-box AI security review that reads your source, reasons about the actual data flow and authorization model, then exploits what it finds in a live sandbox so every reported issue has a working proof-of-concept instead of a noisy static-analysis alert.
Review security boundaries and investigate evidence-backed vulnerabilities across code, APIs, services and command-line tools.
Related guides
- Security Skills for AI Agents: Audit, Hardening and Testing
Compare five security Skills for source audits, secure implementation, Skill inspection, and authorized web and API penetration testing.
How to choose Security skills
Start from the artifact: source code points to review or hardening, a running app points to a pentest workflow, and a binary points to reverse-engineering tools. Have a person review the findings before acting on them.
- Scan a codebase for OWASP Top 10 issues
- Run a penetration-testing workflow against a staging web app
- Analyze a binary or CVE and write remediation notes
