AML.CS0020
Indirect Prompt Injection Threats: Bing Chat Data Pirate
- Type
- Exercise
- When
- 2023
- Actor, as ATLAS names it
- Not stated
- Target
- Microsoft Bing Chat
Techniques, in order
- 1Develop CapabilitiesResource Development · AML.T0017
- 2LLM Prompt ObfuscationDefense Evasion · AML.T0068
- 3LLM Prompt Injection: IndirectExecution · AML.T0051.001
- 4Phishing: Spearphishing via Social Engineering LLMInitial Access · AML.T0052.000
- 5External Harms: User HarmImpact · AML.T0048.003
How these attacks work
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.