using-superpowers
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs high-pressure and absolute language such as 'ABSOLUTELY MUST', 'not negotiable', and 'not optional' to override the agent's autonomous behavior.
- [PROMPT_INJECTION]: It explicitly commands the agent to ignore its own 'rationalization' and context-gathering steps, which are key components of safe and logical decision-making.
- [PROMPT_INJECTION]: The instructions establish a '1% chance' threshold for tool invocation, a tactic designed to bypass the agent's internal relevance filtering and safety guardrails.
Audit Metadata