principle-never-block-on-the-human
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and metadata. It does not include any scripts, executable commands, or network operations.
- [PROMPT_INJECTION]: The core instruction 'Never Block on the Human' is a behavioral guideline for workflow efficiency. The instructions explicitly include safety constraints, requiring user authorization for 'Irreversible actions' such as deleting production data, force-pushing, or sending external messages.
Audit Metadata