using-superpowers
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs strong behavioral enforcement patterns, using 'EXTREMELY-IMPORTANT' blocks and phrases like 'IF A SKILL APPLIES... YOU DO NOT HAVE A CHOICE' and 'This is not negotiable' to mandate tool usage before any agent response.
- [PROMPT_INJECTION]: Instructions explicitly state that 'Superpowers skills override default system behavior,' a common pattern in prompt injection intended to bypass default model constraints. However, the risk is mitigated by a clearly defined 'Instruction Priority' that places user-explicit instructions as the highest priority.
Audit Metadata