using-superpowers

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill employs high-pressure directives such as 'ABSOLUTELY MUST', 'not negotiable', and 'you cannot rationalize your way out of this' to override the agent's autonomy and default reasoning.
  • [PROMPT_INJECTION]: It specifically instructs the agent to ignore typical responses like asking for more context or exploring the codebase, mandating tool usage even when the agent's internal logic suggests otherwise.
  • [NO_CODE]: The skill is composed entirely of markdown instructions and architectural diagrams, with no functional code or script components provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:35 AM