using-superpowers
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses extreme imperative markers such as "EXTREMELY-IMPORTANT", "ABSOLUTELY MUST", "not negotiable", and "not optional" to override the agent's default decision-making and task-prioritization logic.
- [PROMPT_INJECTION]: It mandates the use of the "Skill" tool before any other response or action, even with a "1% chance" of relevance, which overrides standard agent behavior for handling simple queries or requests for clarification.
- [PROMPT_INJECTION]: The instructions include a "Red Flags" table designed to suppress the agent's internal reasoning and rationalization (e.g., "This is just a simple question", "I need more context first"), forcing adherence to the skill's defined workflow over context-aware response generation.
Audit Metadata