principle-never-block-on-the-human
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, network requests, or sensitive file access. It is a set of purely behavioral instructions intended to guide agent autonomy. The instructions explicitly maintain safety boundaries by requiring human confirmation for irreversible actions like data deletion or external messaging. Furthermore, the
disable-model-invocation: trueconfiguration prevents the skill from invoking any tools directly.
Audit Metadata