principle-never-block-on-the-human
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that explicitly override the agent's default behavior regarding human-in-the-loop confirmation for specific tasks.
- It directs the agent to "Never Block on the Human" and states: "Don't ask 'should I do X?' Do X, explain why."
- This instruction encourages the agent to bypass user review for a broad category of "reversible actions" such as writing code or editing notes, which reduces user oversight of the agent's actions.
- The skill attempts to mitigate this by specifying that "irreversible actions" (e.g., force-pushing, deleting production data, or sending external messages) still require confirmation.
Audit Metadata