paperclip-create-agent
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a governed workflow for agent creation, explicitly requiring authorization checks and discouraging attempts to bypass hiring permissions.
- [SAFE]: Integration with external skills, such as those from Vercel Labs, utilizes resources from well-known and trusted organizations for legitimate browser-based capabilities.
- [SAFE]: The skill includes comprehensive security guidance, notably a dedicated Security Engineer template that instructs agents to apply standard frameworks such as STRIDE, OWASP Top 10, and least-privilege principles.
- [SAFE]: Authentication via environment variables follows standard operational practices, accompanied by specific instructions for the agent to avoid searching workspace files for these credentials.
Audit Metadata