review-changes
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a routing logic for code reviews. It utilizes the
gh(GitHub) CLI tool to resolve the current branch's pull request URL (gh pr view --json url), which is a standard and safe operation for a development-oriented skill. - [SAFE]: Argument handling logic is implemented using standard bash
casestatements to prevent invalid flag combinations (e.g., refusing--reportwith--external-review). - [SAFE]: The skill does not perform any direct network operations to external or untrusted domains, nor does it attempt to access sensitive local files. All actions are delegated to other trusted internal components (
review-loop,pr-reviewer,critical). - [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected.
Audit Metadata