adversarial-review
Adversarial AI code review lenses challenging assumptions, testing edge cases, and verifying AI-generated code.
SKILL.mdskills/adversarial-review/SKILL.md
GitHubAdversarial Review Skill
Core Directives
- Treat Code as Hostile: Assume every external input (headers, query params, cookies, payloads, queue messages, LLM outputs) is attacker-controlled.
- Trace Sinks: Follow untrusted data to dangerous interpreters (SQL, shell, DOM, templates, filesystem).
- Challenge Test Sufficiency: Verify whether existing tests actually prove correctness or merely test happy paths.
- Agent Output Verification: Specifically inspect code generated by AI coding agents for hallucinated imports, omitted error handling, and subtly broken edge cases.