using-superpowers

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses imperative and high-pressure language to hijack the agent's operational logic. Evidence includes phrases like 'ABSOLUTELY MUST', 'not negotiable', and 'YOU DO NOT HAVE A CHOICE', which are designed to override the agent's autonomous decision-making.
  • [PROMPT_INJECTION]: The skill provides a 'Red Flags' table that explicitly instructs the agent to ignore its own heuristics, such as the need for context or the simplicity of a task, in favor of following the skill's flow.
  • [PROMPT_INJECTION]: By lowering the threshold for invoking the Skill tool to a '1% chance', the skill significantly expands the attack surface for indirect prompt injection, as the agent is directed to load and 'follow exactly' content from any external skill file it encounters.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:34 PM