using-superpowers

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains instructions that explicitly attempt to override agent behavior and bypass standard safety or logical reasoning processes.
  • Evidence: The skill uses absolute, non-negotiable language such as "ABSOLUTELY MUST", "YOU DO NOT HAVE A CHOICE", "This is not negotiable", and "This is not optional" to force the agent to prioritize tool invocation over all other actions.
  • Evidence: It includes a "Red Flags" section that instructs the agent to stop its own internal reasoning process ("STOP—you're rationalizing") and ignore context-seeking steps like asking clarifying questions.
  • Evidence: The directive to invoke tools even with a "1% chance" of relevance is designed to lower the agent's threshold for executing external instructions, effectively overriding the agent's ability to assess the necessity or safety of an action.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 04:22 PM