using-superpowers
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses extremely forceful language to override the agent's internal reasoning and safety filters. Phrases like 'ABSOLUTELY MUST invoke the skill', 'This is not negotiable', 'This is not optional', and 'You cannot rationalize your way out of this' are classic markers of instruction bypass techniques designed to force specific behaviors even when the agent's logic might suggest otherwise.
- [PROMPT_INJECTION]: The instructions explicitly command the agent to disregard standard conversational flows, such as asking clarifying questions or gathering context, in favor of immediate tool invocation. This represents an attempt to override the platform's native interaction patterns.
Audit Metadata