AML.CS0029
Google Bard Conversation Exfiltration
- Type
- Exercise
- When
- 2023-11-23
- Actor, as ATLAS names it
- Not stated
- Target
- Google Bard
- ATLAS attributes it to Embrace the Red (security evaluation).
Techniques, in order
- 1LLM Prompt CraftingAI Attack Adaptation · AML.T0065
- 2Acquire InfrastructureResource Development · AML.T0008
- 3Develop CapabilitiesResource Development · AML.T0017
- 4Prompt Infiltration via Public-Facing ApplicationInitial Access · AML.T0093
- 5LLM Prompt Injection: IndirectExecution · AML.T0051.001
- 6LLM Response RenderingExfiltration · AML.T0077
- 7External 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.