using-superpowers
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions and does not contain any executable scripts, binaries, or network operations.
- [PROMPT_INJECTION]: The skill contains directives that override standard agent behavior, specifically the '1% Rule' which forces the agent to prioritize tool invocation based on user triggers. It also explicitly instructs the agent to bypass user confirmation for skill transitions ('You don't need to ask the user before invoking a superpowers skill'). These instructions are intended for workflow efficiency and do not target safety guardrails.
Audit Metadata