requesting-code-review
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses bash commands to retrieve git commit hashes and generate diffs for the review process.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it interpolates external strings (implementation descriptions and plan references) into the reviewer subagent's prompt.\n
- Ingestion points: The template in
code-reviewer.mduses{DESCRIPTION},{PLAN_REFERENCE}, and the contents of git commits.\n - Boundary markers: Absent.\n
- Capability inventory: Access to the local git repository and file system.\n
- Sanitization: No sanitization or validation of variables is performed before interpolation.
Audit Metadata