UTC

AML.CS0029

Google Bard Conversation Exfiltration

Type
Exercise
When
2023-11-23
Actor, as ATLAS names it
Not stated
Target
Google Bard
Techniques, in order
  1. 1LLM Prompt CraftingAI Attack Adaptation · AML.T0065
  2. 2Acquire InfrastructureResource Development · AML.T0008
  3. 3Develop CapabilitiesResource Development · AML.T0017
  4. 4Prompt Infiltration via Public-Facing ApplicationInitial Access · AML.T0093
  5. 5LLM Prompt Injection: IndirectExecution · AML.T0051.001
  6. 6LLM Response RenderingExfiltration · AML.T0077
  7. 7External 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.