using-superpowers

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses imperative and absolute language, such as 'ABSOLUTELY MUST', 'not negotiable', and 'not optional', to constrain the agent's decision-making and force the invocation of tools even at very low confidence thresholds.
  • [PROMPT_INJECTION]: It explicitly instructs the agent to 'override default system behavior' where conflicts occur, effectively attempting to reconfigure the agent's core hierarchy of instructions.
  • [PROMPT_INJECTION]: The '1% chance' rule for tool invocation significantly lowers the agent's internal threshold for taking action, which can lead to unnecessary or unintended tool usage based on ambiguous user input.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 08:40 AM