ps-principle-never-block-on-the-human
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to modify its operational behavior by bypassing human confirmation for tasks deemed 'reversible', using patterns like 'Proceed, then present' and 'Don't ask should I do X?'. This reduces human oversight of the agent's code modifications and decision-making.
- [PROMPT_INJECTION]: The instructions establish safety boundaries by explicitly requiring human confirmation for 'irreversible actions' such as deleting production data or sending external messages, which helps mitigate the risk associated with increased autonomy.
Audit Metadata