Activity timeline
AML.T0051.001 first appeared in tracked threats on and was most recently reported on . The busiest month was 2026-08 with 4 reports, and 11 of the 11 threats were reported in the twelve months to 2026-09.
How adversaries use it
AML.T0051.001 LLM Prompt Injection: Indirect is catalogued by MITRE ATLAS under the Execution (ATLAS) tactic in the ATLAS matrix, as a sub-technique of AML.T0051 LLM Prompt Injection. Threadlinqs maps 11 of 2623 tracked threats (0.4%) to it; by severity that is 2 critical, 7 high, 2 medium.
Threats that use AML.T0051.001 most often also use T1027 Obfuscated Files or Information (5 threats), T1036 Masquerading (5 threats), T1213 Data from Information Repositories (5 threats), AML.T0053 AI Agent Tool Invocation (4 threats), AML.T0054 LLM Jailbreak (4 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.
1 tracked threat actor appear in the threats that use AML.T0051.001; the most frequent are Jade Sleet (1).
Threat actors using it
Tracked threats
11 tracked threats use AML.T0051.001.
- SalesBleed: Indirect Prompt Injection Enables Zero-Click CRM Data Exfiltration in Salesforce Agentforcehigh
- Jade Sleet (North Korea) Compromises Indian IT Provider via FLATROOF and ROOFDECK macOS Backdoorshigh
- OpenAI GPT-6 Astra Reaches 'Critical' Cybersecurity Capability Threshold; Attempted Supply-Chain Attacks and…critical
- Zero-Click Cryptographic Context Injection Attack Exfiltrates Grok Chat Data via Malicious Webpageshigh
- 91 Spring Framework CVEs Disclosed by Broadcom, Including Critical Deserialization Flaw CVE-2026-59285critical
- Claude in Chrome Prompt Injection Steals Gmail Codes to Hijack Slack, X, and Claude.ai Accountshigh
- OWASP GenAI LLM Top 10 2026 — Community-Driven Security Guidance for AI Applicationsmedium
- Indirect Prompt Injection via Web Content Targets AI Agents (SEO Poisoning + Payment Scam / Typosquat…medium
- macOS.Gaslight — DPRK-aligned Rust Backdoor & Infostealer with Analyst-Targeting Prompt-Injection…high
- AI Supply Chain Abuse — 575 Trojanized OpenClaw/ClawHub Skills + Hugging Face Malware Staging (Acronis TRU)high
- CVE-2026-26133: Cross-Prompt Injection in Microsoft Copilot Email/Teams Summarization Enables AI-Mediated…high
Detection coverage
Threadlinqs maintains 19 detection rules mapped to AML.T0051.001 (SPL 9, KQL 5, Sigma 5). Rule content is available to Blue tier accounts and above; this page shows counts only.
Parent technique
AML.T0051 LLM Prompt Injection — 19 tracked threats at the technique level.