UTC

AML.CS0024

Morris II Worm: RAG-Based Attack

Type
Exercise
When
2024-03-05
Actor, as ATLAS names it
Stav Cohen, Ron Bitton, Ben Nassi
Target
RAG-based e-mail assistant
Techniques, in order
  1. 1AI Model Inference API AccessAI Model Access · AML.T0040
  2. 2LLM Prompt CraftingAI Attack Adaptation · AML.T0065
  3. 3Verify AttackAI Attack Adaptation · AML.T0042
  4. 4Prompt Infiltration via Public-Facing ApplicationInitial Access · AML.T0093
  5. 5RAG PoisoningPersistence · AML.T0070
  6. 6LLM Prompt Injection: TriggeredExecution · AML.T0051.002
  7. 7LLM JailbreakDefense Evasion · AML.T0054
  8. 8LLM Prompt Self-ReplicationPersistence · AML.T0061
  9. 9Data from AI Services: RAG DatabasesCollection · AML.T0085.000
  10. 10Exfiltration via Cyber MeansExfiltration · AML.T0025
  11. 11LLM Prompt PropagationLateral Movement · AML.T0143
  12. 12External Harms: User HarmImpact · AML.T0048.003
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.