Threadlinqs IntelligenceStart free

ATLAS techniqueExecution (ATLAS)

AML.T0051 LLM Prompt Injection

Execution (ATLAS)ATLAS

As of 2026-10-05, AML.T0051 (LLM Prompt Injection) appears in 19 tracked threats, first reported 2026-07-02 and most recently 2026-10-04, with linked actors including Cleaver, MiniMax, Moonshot AI; it most often appears alongside T1027 (Obfuscated Files or Information).

Tracked threats
195 critical, 7 high, 7 medium
First seen
2026-07-02
Last seen
2026-10-04
Threat actors
4In the threats using it
Detection rules
50Blue tier and above

Data as of:

Activity timeline

AML.T0051 first appeared in tracked threats on and was most recently reported on . The busiest month was 2026-08 with 8 reports, and 19 of the 19 threats were reported in the twelve months to 2026-10.

How adversaries use it

AML.T0051 LLM Prompt Injection is catalogued by MITRE ATLAS under the Execution (ATLAS) tactic in the ATLAS matrix. Threadlinqs maps 19 of 2623 tracked threats (0.7%) to it; by severity that is 5 critical, 7 high, 7 medium.

Threats that use AML.T0051 most often also use T1027 Obfuscated Files or Information (10 threats), T1566 Phishing (9 threats), T1204 User Execution (7 threats), AML.T0054 LLM Jailbreak (6 threats), T1583 Acquire Infrastructure (6 threats). These are the techniques an intrusion set tends to chain with it, so they are the natural next places to look when it is observed.

4 tracked threat actors appear in the threats that use AML.T0051; the most frequent are Cleaver (2), MiniMax (2), Moonshot AI (2), StepFun (2).

Threat actors using it

Tracked threats

19 tracked threats use AML.T0051.

Detection coverage

Threadlinqs maintains 50 detection rules mapped to AML.T0051 (SPL 17, KQL 15, Sigma 18). Rule content is available to Blue tier accounts and above; this page shows counts only.

50 detection rules (SPL/KQL/Sigma) · Blue and above. Compare plans

Sub-techniques