pr-review-expert

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were found in the skill's instructions or metadata. All capabilities are aligned with the stated purpose of code review.
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and standard Unix utilities (such as grep, jq, sed, wc, and sort) to gather and process PR data. These commands are used to identify potential security risks (like SQL injection or hardcoded secrets) within the codebase being reviewed and do not present a risk to the agent's environment.
  • [DATA_EXFILTRATION]: The skill fetches diffs and metadata from version control systems. There is no evidence of data being sent to external, unauthorized, or untrusted endpoints. The data processing remains local to the review task.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:12 AM