using-superpowers

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill employs extreme imperative language and override markers intended to bypass the agent's standard reasoning process. Phrases such as 'ABSOLUTELY MUST', 'not negotiable', 'not optional', and 'You cannot rationalize your way out of this' are used to force specific behaviors.
  • [PROMPT_INJECTION]: The instructions command the agent to disregard its own internal 'rationalizations' or 'thoughts' (e.g., 'This is just a simple question', 'I need more context first'), which is a technique typically used to override system-level decision-making logic.
  • [PROMPT_INJECTION]: By establishing a '1% chance' threshold for invoking the Skill tool, the instructions effectively lower the agent's confidence requirements for taking action, making it more susceptible to triggering tools based on minor or potentially deceptive cues in user prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 12:42 PM