using-superpowers
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Use of extreme imperative language and override markers such as 'ABSOLUTELY MUST', 'not negotiable', and 'not optional' to force specific agent behaviors.
- [PROMPT_INJECTION]: Instructions explicitly attempt to suppress the AI's internal reasoning or discretion, labeling standard logic as 'rationalizing' and demanding tool invocation before providing even clarifying questions.
- [PROMPT_INJECTION]: The skill dictates a rigid 'Rule' that bypasses the agent's ability to evaluate task complexity, requiring tool use if there is even a '1% chance' of relevance.
Audit Metadata