The Agent Skills Directory

[SAFE]: The skill provides a structured framework for code review and security audits. It consists entirely of markdown instructions and configuration, with no executable scripts or subprocess calls detected.
[PROMPT_INJECTION]: The skill is designed to analyze external data (code snippets) provided for auditing. Ingestion points: External code provided via direct invocation or workflow dispatch. Boundary markers: Absent; the skill does not currently define delimiters to wrap audited code. Capability inventory: None; the skill lacks file-write or network-access capabilities. Sanitization: Not applicable as the skill performs static analysis only.

security-auditor