AML.CS0021
ChatGPT Conversation Exfiltration
- Type
- Exercise
- When
- 2023-05
- Actor, as ATLAS names it
- Not stated
- Target
- OpenAI ChatGPT
- ATLAS attributes it to Embrace the Red (security evaluation).
- On ShieldMap: ChatGPT (matched by name in the target).
Techniques, in order
- 1LLM Prompt CraftingAI Attack Adaptation · AML.T0065
- 2Stage CapabilitiesResource Development · AML.T0079
- 3Drive-by CompromiseInitial Access · AML.T0078
- 4LLM Prompt Injection: IndirectExecution · AML.T0051.001
- 5LLM Response RenderingExfiltration · AML.T0077
- 6AI Agent Tool InvocationPrivilege Escalation · AML.T0053
- 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.