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
- 1AI Model Inference API AccessAI Model Access · AML.T0040
- 2LLM Prompt CraftingAI Attack Adaptation · AML.T0065
- 3Verify AttackAI Attack Adaptation · AML.T0042
- 4Prompt Infiltration via Public-Facing ApplicationInitial Access · AML.T0093
- 5RAG PoisoningPersistence · AML.T0070
- 6LLM Prompt Injection: TriggeredExecution · AML.T0051.002
- 7LLM JailbreakDefense Evasion · AML.T0054
- 8LLM Prompt Self-ReplicationPersistence · AML.T0061
- 9Data from AI Services: RAG DatabasesCollection · AML.T0085.000
- 10Exfiltration via Cyber MeansExfiltration · AML.T0025
- 11LLM Prompt PropagationLateral Movement · AML.T0143
- 12External Harms: User HarmImpact · AML.T0048.003
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.