using-superpowers
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses aggressive, imperative language ('ABSOLUTELY MUST', 'not negotiable') to enforce its workflow and specifically instructs the agent to ignore its own internal logic or 'rationalization' regarding when to skip skill usage.
- [PROMPT_INJECTION]: Instructions explicitly direct the agent to override its default system prompt, assigning it the 'lowest priority' compared to the skill's instructions.
- [PROMPT_INJECTION]: The requirement to invoke the Skill tool before any response, including clarifying questions, mandates an external tool-call before the agent fully clarifies the user's intent, potentially bypassing safety context provided by the user.
Audit Metadata