ia-receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured process for handling code review feedback using the GitHub API (
gh api) to fetch and respond to comments. This usage is consistent with its stated purpose of managing pull request reviews. - [SAFE]: It addresses potential risks from untrusted external input (indirect prompt injection) by mandating a 'Verify before implementing' principle. It instructs the agent to be skeptical of automated review agents and to verify all suggestions against the codebase, project conventions, and technical evidence.
- [SAFE]: The skill includes robust logic for triaging feedback into categories like AUTO-FIX, AUTO-DECLINE, and ESCALATE, ensuring that complex architectural decisions or ambiguous suggestions are surfaced for human review.
- [SAFE]: No obfuscation, persistence mechanisms, unauthorized privilege escalation, or hardcoded credentials were found in the instructions or metadata.
Audit Metadata