receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to process code review feedback from external sources, which constitutes an ingestion point for untrusted data. This presents a potential surface for indirect prompt injection if a reviewer includes malicious instructions in their feedback. However, the skill includes explicit mitigations by instructing the agent to 'verify before implementing' and to be 'skeptical' of external feedback, checking it against the 'codebase reality' and context before taking action.
- Tool Interaction (GitHub CLI): The instructions specify the use of the GitHub API (
gh api) for replying to review comments. This is a standard administrative task for a coding assistant and is used here to ensure replies are correctly threaded within the PR context rather than posted as global comments. - Automated Behavior Constraints: The skill sets specific behavioral constraints, such as avoiding performative gratitude ('Thanks') and requiring full understanding before partial implementation. These are stylistic and operational guardrails that do not introduce security vulnerabilities.
Audit Metadata