AML.CS0071
Multi-Agent Framework Compromises Taiwanese Government Systems
- Type
- Incident
- When
- 2026-07-01 to 2026-07-04
- Actor, as ATLAS names it
- Unknown Chinese-language actor
- Target
- Taiwanese government agencies and connected government systems
Techniques, in order
- 1Autonomous Attack OrchestrationAI Attack Adaptation · AML.T0124
- 2Autonomous Attack-Path AdaptationAI Attack Adaptation · AML.T0117
- 3Autonomous AI Agent Communication: Direct Agent CommunicationAI Attack Adaptation · AML.T0118.001
- 4Autonomous ReconnaissanceReconnaissance · AML.T0116
- 5Active ScanningReconnaissance · AML.T0006
- 6Data from Information RepositoriesCollection · AML.T0036
- 7Valid AccountsInitial Access · AML.T0012
- 8Valid AccountsLateral Movement · AML.T0012
- 9Exploit Public-Facing ApplicationInitial Access · AML.T0049
- 10Automated CollectionCollection · AML.T0126
- 11Exfiltration via Cyber MeansExfiltration · AML.T0025
Software used
- Hermes Agent · Tool
- OpenClaw · Tool
- Tesseract OCR · Tool
References
- Inside a Multi-Agent AI Framework Used to Compromise Government Entities in Asia
- Overseas hackers launch AI-agent attacks against government agencies; MODA activates coordinated response and strengthens cyber defenses
- China-linked hackers hit Taiwan in unprecedented 'autonomous' AI cyber attack
- AIID - Incident 1646: Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records
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.