using-plan-and-execute
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs absolute and forceful language to override the agent's standard decision-making processes and discretion regarding tool usage.
- Evidence: The text uses extreme markers such as "EXTREMELY-IMPORTANT," "ABSOLUTELY MUST," "not negotiable," "not optional," and "You cannot rationalize your way out of this."
- Evidence: It establishes a "Mandatory First Response Protocol" and threatens that failing to follow the checklist results in "automatic failure."
- Context: This framing is designed to bypass the agent's internal evaluation of task relevance, forcing the execution of other skills even if the agent's own reasoning suggests they are not applicable or necessary.
Audit Metadata