agent
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for implementing AI functionality using the @convex-dev/agent library. No malicious patterns or security risks were identified.
- [EXTERNAL_DOWNLOADS]: The skill references the '@convex-dev/agent' Node.js package, which is a library specifically designed for the Convex platform infrastructure.
- [CREDENTIALS_UNSAFE]: The instructions explicitly advise storing LLM API keys in the Convex environment using best practices for secret management, rather than exposing them on the client side.
Audit Metadata