AML.CS0030
LLMjacking: Stolen Cloud Credentials Used to Access Cloud LLM Services.
- Type
- Incident
- When
- 2024-05-06
- Actor, as ATLAS names it
- Unknown
- Target
- Cloud-Based LLM Services
Techniques, in order
- 1Exploit Public-Facing ApplicationInitial Access · AML.T0049
- 2Unsecured CredentialsCredential Access · AML.T0055
- 3Compromise AccountsResource Development · AML.T0139
- 4Valid AccountsInitial Access · AML.T0012
- 5Obtain Capabilities: Software ToolsResource Development · AML.T0016.001
- 6Enterprise Resource DiscoveryDiscovery · AML.T0075
- 7Acquire Infrastructure: AI Service ProxiesResource Development · AML.T0008.005
- 8External Harms: Financial HarmImpact · AML.T0048.000
Software used
- keychecker · Tool
- OAI Reverse Proxy · Tool
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.