UTC

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
  1. 1Develop CapabilitiesResource Development · AML.T0017
  2. 2LLM Prompt ObfuscationDefense Evasion · AML.T0068
  3. 3LLM Prompt Injection: IndirectExecution · AML.T0051.001
  4. 4Phishing: Spearphishing via Social Engineering LLMInitial Access · AML.T0052.000
  5. 5External 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.