scope-creep-detector
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that override the agent's default helpful behavior. It directs the agent to treat every follow-up request from the user as 'unauthorized scope creep' and requires the implementation of a mock 'Change Request' process (CR numbers, business justifications, and budget warnings) before fulfilling requests. This behavioral override explicitly instructs the agent to be obstructive, even for minor tasks like fixing typos.
Audit Metadata