UTC

AML.CS0069

GTG-1002 Claude Code Espionage Campaign

Type
Incident
When
2025-09
Actor, as ATLAS names it
Not stated
Target
30 entities in the technology, financial, chemical, and government sectors
Techniques, in order
  1. 1AI Model Inference API AccessAI Model Access · AML.T0040
  2. 2LLM Prompt Injection: DirectExecution · AML.T0051.000
  3. 3LLM JailbreakDefense Evasion · AML.T0054
  4. 4Obtain Capabilities: Software ToolsResource Development · AML.T0016.001
  5. 5Compromise InfrastructureResource Development · AML.T0128
  6. 6Deploy AI AgentExecution · AML.T0103
  7. 7Autonomous Attack-Path AdaptationAI Attack Adaptation · AML.T0117
  8. 8Autonomous ReconnaissanceReconnaissance · AML.T0116
  9. 9Active ScanningReconnaissance · AML.T0006
  10. 10Develop Capabilities: Autonomous Exploit DevelopmentResource Development · AML.T0017.001
  11. 11Exploit Public-Facing ApplicationInitial Access · AML.T0049
  12. 12Enterprise Resource DiscoveryDiscovery · AML.T0075
  13. 13Enterprise Environment DiscoveryDiscovery · AML.T0089
  14. 14Unsecured CredentialsCredential Access · AML.T0055
  15. 15Valid AccountsLateral Movement · AML.T0012
  16. 16Create AccountPersistence · AML.T0125
  17. 17Data from Information RepositoriesCollection · AML.T0036
  18. 18Data from Local SystemCollection · AML.T0037
  19. 19Automated CollectionCollection · AML.T0126
  20. 20Data StagedCollection · AML.T0127
  21. 21Exfiltration via AI User InterfaceExfiltration · AML.T0136
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.