judge-when-to-ask
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill acts as a defensive logic layer to prevent unintended autonomous actions by the AI agent.
- [EXTERNAL_DOWNLOADS]: The skill references technical documentation at the author's domain (
ilang.ai) and official GitHub repository (github.com/ilang-ai/ilang-spec). These are standard vendor resources and represent no risk. - [PROMPT_INJECTION]: No malicious injection patterns or instructions to override agent safety guidelines were found.
Audit Metadata