using-superpowers

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains instructions designed to override the agent's default behavioral patterns and internal reasoning process.
  • Evidence: In SKILL.md, the text states: "Superpowers skills override default system prompt behavior, but user instructions always take precedence."
  • Evidence: The skill uses strong, non-negotiable imperatives to force tool usage: "YOU ABSOLUTELY MUST invoke the skill... IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT. This is not negotiable. This is not optional."
  • Evidence: A "Red Flags" section specifically instructs the agent to ignore its own common-sense reasoning or productivity-based rationalizations (e.g., "This is just a simple question" or "Let me gather information first") in favor of strict adherence to the skill-check workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:14 AM