AML.CS0068
Autonomous OpenAI Evaluation Agents Compromise Hugging Face Infrastructure
- Type
- Incident
- When
- 2026-07-09 to 2026-07-13
- Actor, as ATLAS names it
- Autonomous OpenAI Agents
- Target
- Hugging Face Infrastructure
Techniques, in order
- 1Autonomous Attack-Path AdaptationAI Attack Adaptation · AML.T0117
- 2Develop Capabilities: Autonomous Exploit DevelopmentResource Development · AML.T0017.001
- 3Exploitation of Remote ServicesLateral Movement · AML.T0122
- 4Autonomous AI Agent Communication: Communication via Shared ArtifactsAI Attack Adaptation · AML.T0118.000
- 5Autonomous ReconnaissanceReconnaissance · AML.T0116
- 6Generate Malicious CommandsAI Attack Adaptation · AML.T0102
- 7Exploit Public-Facing ApplicationInitial Access · AML.T0049
- 8Command and Scripting InterpreterExecution · AML.T0050
- 9Enterprise Resource DiscoveryDiscovery · AML.T0075
- 10Enterprise Environment DiscoveryDiscovery · AML.T0089
- 11AI Agent Environment ReconstructionPersistence · AML.T0121
- 12Cyber Communication ChannelCommand and Control · AML.T0072
- 13Obfuscated Files or InformationDefense Evasion · AML.T0123
- 14Unsecured CredentialsCredential Access · AML.T0055
- 15Valid AccountsInitial Access · AML.T0012
- 16Exploit Automated Artifact Processing PipelineInitial Access · AML.T0119
- 17Data from Local SystemCollection · AML.T0037
- 18AI Artifact RepositoryCommand and Control · AML.T0120
- 19Use Alternate Authentication Material: Application Access TokenLateral Movement · AML.T0091.000
- 20Escape to HostPrivilege Escalation · AML.T0105
- 21Valid AccountsLateral Movement · AML.T0012
- 22Data from Information RepositoriesCollection · AML.T0036
- 23Exfiltration via Cyber MeansExfiltration · AML.T0025
References
- OpenAI and Hugging Face Partner to Address Security Incident During Model Evaluation
- Security Incident Disclosure - July 2026
- Anatomy of a Frontier Lab Agent Intrusion
- The Breaking News: The OpenAI-Hugging Face Incident
- JFrog and OpenAI Collaboration on Zero-Day Security Findings
- Hugging Face Incident and the Road Ahead
- OpenAI Hugging Face Incident Investigation
- AIID - Incident 1604: OpenAI Models Reportedly Compromised Hugging Face Production Infrastructure During Cybersecurity Evaluation
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.