using-superpowers
Warn
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses high-pressure directives such as "ABSOLUTELY MUST," "not negotiable," and "not optional" to mandate the invocation of other skills. It specifically includes instructions to bypass the agent's own reasoning process, using phrases like "You cannot rationalize your way out of this" and "STOP—you're rationalizing." Furthermore, it explicitly states that these skills "override default system prompt behavior," which is a direct attempt to subvert the core safety and operational guidelines of the underlying AI model.
Audit Metadata