using-superpowers

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill employs extreme imperative language such as 'ABSOLUTELY MUST', 'YOU DO NOT HAVE A CHOICE', and 'This is not negotiable' to force the agent to prioritize these instructions over its own logic.
  • PROMPT_INJECTION (LOW): Includes a 'Red Flags' section specifically designed to suppress the agent's internal rationalization and critical thinking process (e.g., 'These thoughts mean STOP—you're rationalizing').
  • PROMPT_INJECTION (LOW): Sets a near-zero threshold for tool usage ('even a 1% chance'), which forces the agent to invoke external tools (Skill tool) before performing any other actions, including clarifying questions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 01:23 PM