using-superpowers

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill employs highly imperative and coercive language to mandate specific agent behavior. Phrases like "EXTREMELY-IMPORTANT", "ABSOLUTELY MUST", "not negotiable", and "not optional" are used to override the agent's default tool-use logic. It specifically instructs the agent to ignore its own reasoning ("You cannot rationalize your way out of this") and forces skill invocation even for clarifying questions. While intended to enforce a workflow, this represents a significant attempt to hijack the agent's decision-making process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:54 AM
Security Audit — agent-trust-hub — using-superpowers