receiving-code-review

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of instructions aimed at ensuring technical correctness and verification during the code review process.
  • [COMMAND_EXECUTION]: The skill includes instructions for using the GitHub CLI (gh api) to interact with pull request comments.
  • [PROMPT_INJECTION]: The skill sets strong constraints on the agent's communication style (e.g., forbidding specific polite phrases). These are stylistic directives and do not represent an attempt to bypass AI safety controls.
  • [SAFE]: (Indirect Prompt Injection Surface) 1. Ingestion points: External code review feedback (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: GitHub API interaction and codebase modification (SKILL.md). 4. Sanitization: The skill enforces a mandatory verification and reasoning process before any changes are implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 01:08 PM