using-superpowers
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill employs extremely imperative language such as 'ABSOLUTELY MUST', 'not negotiable', and 'not optional' to force the agent to prioritize tool invocation over its standard operational logic.
- [PROMPT_INJECTION]: It includes a 'Red Flags' section specifically designed to train the agent to ignore internal reasoning or hesitations, such as the need for more context or simple clarifications, which could be leveraged to bypass safety filters or user intent.
- [PROMPT_INJECTION]: By lowering the threshold for skill invocation to a '1% chance', the skill significantly increases the agent's exposure to potentially untrusted content from other skills before the user has a chance to intervene.
Audit Metadata