mind-parameter-modification

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (LOW): The skill uses terminology like 'modify cognitive parameters' which is a known pattern for attempting to override an AI's internal safety logic.
  • [Metadata Poisoning] (MEDIUM): The title and description are deceptive, using pseudo-technical jargon to package an adversarial prompt injection intent as a legitimate skill.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:43 PM