review-pr
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) to perform actions like viewing PR metadata and fetching diffs. These are standard, legitimate operations for the skill's intended purpose. - [DATA_EXFILTRATION]: The skill accesses PR data from GitHub to perform its analysis. It does not attempt to access sensitive local files or transmit data to unauthorized external endpoints.
- [PROMPT_INJECTION]: The skill processes external data (PR diffs) which could contain malicious instructions. It mitigates this risk by requiring that all comments are created as 'pending' and explicitly forbidding automatic submission or confirmation of the review, maintaining human oversight.
Audit Metadata