AML.CS0062
RCE Vulnerability in Semantic Kernel Search Plugin
- Type
- Exercise
- When
- 2026-05-07
- Actor, as ATLAS names it
- Not stated
- Target
- Semantic Kernel
- ATLAS attributes it to Microsoft Defender Security Research Team (security evaluation).
Techniques, in order
- 1LLM Prompt CraftingAI Attack Adaptation · AML.T0065
- 2AI-Enabled Product or ServiceAI Model Access · AML.T0047
- 3LLM Prompt Injection: DirectExecution · AML.T0051.000
- 4AI Agent Tool InvocationPrivilege Escalation · AML.T0053
- 5Command and Scripting InterpreterExecution · AML.T0050
- 6Machine CompromiseImpact · AML.T0112
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.