using-superpowers
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs aggressive language such as 'ABSOLUTELY MUST', 'not negotiable', and 'not optional' to override the agent's autonomous decision-making process.\n- [PROMPT_INJECTION]: It includes a 'Red Flags' section designed to suppress the agent's internal logic and safety assessments, labeling standard reasoning (e.g., 'I need more context first') as invalid 'rationalizations' to be ignored.\n- [PROMPT_INJECTION]: The instructions mandate the invocation of tools based on a '1% chance' threshold, which significantly lowers the bar for tool execution and may bypass default efficiency or safety heuristics.
Audit Metadata