using-superpowers

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill employs high-pressure language and imperative markers such as 'EXTREMELY-IMPORTANT', 'MUST', and 'HARD RULE' to override the agent's default logic and decision-making regarding tool use.
  • [PROMPT_INJECTION]: It dictates a '1% chance' rule that forces the agent to prioritize the invocation of external skills (tools) over providing direct responses or asking for clarifications, which acts as a behavioral override of the agent's core instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 08:50 AM