code-review
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized data access behaviors were detected.
- [EXTERNAL_DOWNLOADS]: The skill contains instructions to fetch updated web interface guidelines and repository metadata from Vercel Labs' official GitHub presence. These references target a well-known and trusted organization and are intended for maintaining the skill's reference data.
- [INDIRECT_PROMPT_INJECTION]: As a code review tool, the skill naturally ingests untrusted data in the form of branch diffs and pull request content. The instructions emphasize a read-only approach and specific audit axes (Standards, Spec, Interface), which provides structure for the analysis of external code.
- [COMMAND_EXECUTION]: The skill instructions describe a workflow for launching parallel sub-agents (reviewers) and using git commands to capture snapshots of code. These operations are aligned with the primary purpose of performing an independent code review.
Audit Metadata