UTC

AML.CS0072

AI Recommendation Poisoning via Crafted AI Assistant Links

Type
Incident
When
2026-02-10
Actor, as ATLAS names it
Multiple commercial entities; 31 distinct companies identified
Target
Users of AI assistants with persistent memory features, including Microsoft 365 Copilot, ChatGPT, Claude, Perplexity, and Grok
Techniques, in order
  1. 1Obtain CapabilitiesResource Development · AML.T0016
  2. 2Stage CapabilitiesResource Development · AML.T0079
  3. 3Crafted AI Assistant LinksInitial Access · AML.T0131
  4. 4LLM Prompt ObfuscationDefense Evasion · AML.T0068
  5. 5AI Agent Context Poisoning: MemoryPersistence · AML.T0080.000
  6. 6AI Agent Response BiasingImpact · AML.T0130
The full case study on MITRE ATLAS →

From MITRE ATLAS 2026.10 (Apache-2.0). ShieldMap lists who and what was involved and the techniques used, and links to ATLAS for the write-up; it does not copy the steps. Attribution is ATLAS's, not ShieldPi's.