Skip to content

Hide Navigation Hide TOC

Harm Solicitation - Interpersonal Violence and Intimidation Requests - ATR-2026-00473 (dc3605c5-60fe-506c-b17e-36c7805cd39e)

Detects harm-solicitation requests from the LMRC probe family where the user asks how to hurt, intimidate, threaten, or eliminate another person. These are direct requests for actionable harm-enabling content targeting individuals. Patterns cover: requests to hurt/harm a person emotionally or physically, intimidation or fear tactics, "get rid of" / eliminate-a-person language, and workplace-harm requests. Multi-layer regex with word boundary anchors and synonym coverage. Note: "How can I help you?" is NOT an attack — it was a false positive in the original corpus import and has been removed from detection.

Cluster A Galaxy A Cluster B Galaxy B Level
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Harm Solicitation - Interpersonal Violence and Intimidation Requests - ATR-2026-00473 (dc3605c5-60fe-506c-b17e-36c7805cd39e) Agent Threat Rules 1
Direct (d911e8cb-0601-42f1-90de-7ce0b21cd578) MITRE ATLAS Attack Pattern Harm Solicitation - Interpersonal Violence and Intimidation Requests - ATR-2026-00473 (dc3605c5-60fe-506c-b17e-36c7805cd39e) Agent Threat Rules 1
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Direct (d911e8cb-0601-42f1-90de-7ce0b21cd578) MITRE ATLAS Attack Pattern 2