Skip to content

Hide Navigation Hide TOC

Persona-Based Moral Constraint Removal Jailbreak - ATR-2026-00235 (70030760-7ecd-5498-92a5-ba0ae3667556)

Detects jailbreak attempts that establish alternate personas explicitly designed to bypass moral and ethical constraints. This attack pattern instructs the AI to "take up" or "adopt" a named persona that is specifically described as being "not restrained by morals, ethics, or virtues" or similar moral constraint removal language. Often includes template placeholders for follow-up injection. This variant bypasses existing named-persona detection by using less common persona names (like "naD") while explicitly stating moral/ethical unrestraint.

Cluster A Galaxy A Cluster B Galaxy B Level
LLM Jailbreak (172427e3-9ecc-49a3-b628-96b824cc4131) MITRE ATLAS Attack Pattern Persona-Based Moral Constraint Removal Jailbreak - ATR-2026-00235 (70030760-7ecd-5498-92a5-ba0ae3667556) Agent Threat Rules 1