Skip to content

Hide Navigation Hide TOC

DAN Persona Jailbreak - Absolute Obedience Character Framing - ATR-2026-00490 (d4c01179-067f-5865-b252-9c18f41d31fc)

Detects DAN-family jailbreak attempts that establish unconditionally obedient personas by assigning a character name and declaring absolute subservience or mandatory compliance. Attack pattern: assign a named character identity, then assert the character must follow all commands regardless of content or policies. Covers "subservient", "must answer", "remember previous interactions to maintain character", and task-assignment-via-character framings. Generalised from garak 'dan' probe corpus cluster 'in order to'.

Cluster A Galaxy A Cluster B Galaxy B Level
DAN Persona Jailbreak - Absolute Obedience Character Framing - ATR-2026-00490 (d4c01179-067f-5865-b252-9c18f41d31fc) Agent Threat Rules LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern 1
DAN Persona Jailbreak - Absolute Obedience Character Framing - ATR-2026-00490 (d4c01179-067f-5865-b252-9c18f41d31fc) Agent Threat Rules Direct (d911e8cb-0601-42f1-90de-7ce0b21cd578) MITRE ATLAS Attack Pattern 1
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Direct (d911e8cb-0601-42f1-90de-7ce0b21cd578) MITRE ATLAS Attack Pattern 2