code-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external feedback and git metadata, which could contain malicious instructions designed to influence the agent. • Ingestion points: External reviewer comments and feedback (references/code-review-reception.md) and git logs/SHAs (references/requesting-code-review.md). • Boundary markers: The protocol uses a manual reasoning chain (READ -> UNDERSTAND -> VERIFY -> EVALUATE) and YAGNI checks to validate suggestions. • Capability inventory: Shell command execution (git, grep, and arbitrary verification commands), file system access for code inspection, and subagent dispatch via the Task tool. • Sanitization: Relies on the agent's technical evaluation and verification against the codebase rather than automated sanitization of external inputs.
- [DYNAMIC_EXECUTION]: The 'Verification Gates' protocol in references/verification-before-completion.md requires the agent to dynamically identify and execute shell commands (e.g., tests, builds, linters) to confirm the status of the work before making completion claims.
Audit Metadata