security-research
Runs a parallel team of vulnerability hunters and PoC engineers to audit a codebase, prove which findings are actually exploitable, and produce a severity-calibrated security report.
What it does
Team Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel, prove exploitability, classify root causes, and calibrate severity by actual exploitability. Use for security review, vulnerability research, exploitability audit, pre-release security check, threat model validation, and `/security-research`. Triggers: 'security-research', 'security research', 'security review', 'vulnerability audit', 'exploitability audit', '보안 리뷰', '취약점 감사'.
Quality judgment
A well-structured, operationally detailed skill with clear preconditions, a concrete team roster, phased workflow, severity discipline, and a strong report template; triggers are explicit and multilingual. It loses points for lacking concrete worked examples of findings/PoCs, thin failure handling beyond a single category retry, and heavy coupling to specific team_* tool semantics that may not generalize.