using-superpowers

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): The skill uses high-pressure language ('ABSOLUTELY MUST', 'not negotiable', 'automatic failure') to dictate agent behavior and redefine task execution parameters.
  • PROMPT_INJECTION (LOW): Instructions explicitly command the agent to disregard user preferences if they conflict with the skill's mandatory workflows ('Your human partner's specific instructions... NOT permission to skip brainstorming').
  • NO_CODE (SAFE): No executable scripts or external dependencies were found within the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:43 PM