agent-design-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions for performing a design review. It does not utilize any tools, perform network operations, or access the file system.
- [SAFE]: The instructions include specific guidance for identifying and mitigating security risks in agents, such as requiring human-in-the-loop confirmation gates for high-impact actions and handling untrusted tool output as data rather than instructions to prevent prompt injection.
- [SAFE]: No obfuscation, credentials, or persistence mechanisms were detected in the skill file.
Audit Metadata