code-review
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured and defensive guidelines for code review, focusing on correctness, security (Pass I), and data integrity.
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard local development tools (git) and the GitHub CLI (gh) to retrieve diffs and PR metadata. These operations are performed within the user's authenticated environment and are standard for the described purpose.
- [PROMPT_INJECTION]: The instructions explicitly tell the agent to ignore the 'happy path' and 'trusted intent' expressed by authors in comments or PR descriptions, which is a robust defense against being misled by instructions embedded in the code or metadata being reviewed.
- [DATA_EXFILTRATION]: Analysis of the network and file operations shows no patterns of unauthorized data exfiltration or credential harvesting.
Audit Metadata