UTC

AML.CS0052

LLMSmith: RCE Vulnerabilities in LLM-Integrated Applications

Type
Exercise
When
2025-02-27
Actor, as ATLAS names it
Researchers at University of Chinese Academy of Sciences, Shandong University, and University of New South Wales
Target
LLM Integration Frameworks
Techniques, in order
  1. 1Develop CapabilitiesResource Development · AML.T0017
  2. 2Search Application RepositoriesReconnaissance · AML.T0004
  3. 3Discover AI Agent Configuration: Call ChainsDiscovery · AML.T0084.003
  4. 4LLM Prompt CraftingAI Attack Adaptation · AML.T0065
  5. 5Exploit Public-Facing ApplicationInitial Access · AML.T0049
  6. 6LLM Prompt Injection: DirectExecution · AML.T0051.000
  7. 7LLM JailbreakDefense Evasion · AML.T0054
  8. 8AI Agent Tool InvocationPrivilege Escalation · AML.T0053
  9. 9Command and Scripting InterpreterExecution · AML.T0050
  10. 10Escape to HostPrivilege Escalation · AML.T0105
  11. 11Cyber Communication ChannelCommand and Control · AML.T0072
  12. 12Machine Compromise: Local AI AgentImpact · AML.T0112.000
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.