scenario-team-admin
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured administrative tools for team governance and includes clear instructions for permission checks, such as requiring team-level writes to be performed by human admins over OAuth.\n- [SAFE]: Destructive actions, including member removal and API key deletion, include mandatory instructions for the agent to list and confirm specific targets with the user before proceeding.\n- [SAFE]: The skill explicitly handles API key hygiene by not allowing the creation or retrieval of raw secrets through the agent, instead directing users to a secure web portal.\n- [SAFE]: References to installation commands (e.g.,
npx skills add) target the official vendor repository and are provided as recommendations for the user rather than automated background executions.
Audit Metadata