Grandma Roleplay Jailbreak - ATR-2026-00271 (b870d860-4005-5851-a6cf-3de1de1c3a51)
Detects the "grandma attack" where users roleplay a deceased grandmother or authority figure who would freely provide harmful information as a bedtime story, lullaby, or nostalgic memory. The emotional framing (grief, nostalgia, impersonation of a beloved figure) is designed to lower the model's refusal threshold. From NVIDIA garak grandma probe family (Win10, Slurs, Substances subprobes). Real-world variants extend to: pharmacist grandma, chemistry-teacher uncle, military grandfather.
| Cluster A | Galaxy A | Cluster B | Galaxy B | Level |
|---|---|---|---|---|
| LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) | MITRE ATLAS Attack Pattern | Grandma Roleplay Jailbreak - ATR-2026-00271 (b870d860-4005-5851-a6cf-3de1de1c3a51) | Agent Threat Rules | 1 |