handsfree
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structural instructions for managing agent autonomy, focusing on minimizing user interruptions for routine work.
- [SAFE]: References to external documentation from Anthropic and the Git project are provided for research and context; these targets are well-known, trusted organizations.
- [SAFE]: The instructions explicitly prohibit bypassing security boundaries, host-enforced permissions, or ignoring safety protocols even when the user requests autonomy.
- [SAFE]: The policy documentation includes specific guidance to detect and block instructions hidden in external data, effectively mitigating indirect prompt injection risks by design.
- [SAFE]: No suspicious code execution, network exfiltration, or persistence mechanisms were detected in the skill files.
Audit Metadata