receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the GitHub CLI (gh api) for replying to pull request comments and grep for verifying code usage and applying the YAGNI principle.
- [PROMPT_INJECTION]: The skill processes external reviewer feedback, creating an indirect prompt injection surface (Category 8). 1. Ingestion points: Code review comments from external reviewers. 2. Boundary markers: The skill does not define structural delimiters for the input but uses instructional boundaries. 3. Capability inventory: The agent can execute commands, search files, and perform file modifications. 4. Sanitization: No automatic sanitization is present, but the instructions require manual verification and technical reasoning before implementation.
Audit Metadata