using-superpowers
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill employs aggressive, absolute language ("ABSOLUTELY MUST", "NOT NEGOTIABLE", "NO CHOICE") to override the agent's default behavior and reasoning processes. It specifically instructs the agent to ignore its own internal logic, labeling it as "rationalization" (e.g., "STOP—you're rationalizing") when evaluating if a task requires a skill.
- [PROMPT_INJECTION]: The instructions mandate tool invocation (
Skill) even if there is only a "1% chance" of applicability. This is designed to bypass the agent's standard context evaluation and forced compliance regardless of the agent's own assessment of the user's intent or safety. - [NO_CODE]: The skill consists entirely of markdown instructions and does not contain any executable scripts or configuration files.
Audit Metadata