using-superpowers

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses high-pressure, imperative language (e.g., "ABSOLUTELY MUST", "This is not negotiable", "automatic failure") to override the agent's default operational logic and decision-making. \n- [PROMPT_INJECTION]: It commands the agent to disregard its own internal reasoning or "rationalizations" when deciding whether to apply a skill, which can lower the agent's skepticism toward external instructions. \n- [PROMPT_INJECTION]: The instructions explicitly state that these workflows take precedence over direct human partner instructions, potentially causing the agent to ignore user-specified shortcuts or preferences.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 06:07 PM