AI AgentHigh
Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records
- Occurred
- Jul 1, 2026
- Published
- Aug 13, 2026
- Source
- AI Incident Database
Summary
From July 1–4, 2026, suspected China-linked hackers reportedly used a multi-agent framework built on Hermes and OpenClaw to compromise Taiwanese government systems. The agents reportedly compromised 85 credentials and used persistent access to connected systems to exfiltrate more than 2,564 personnel records. Taiwan later confirmed an overseas AI-assisted campaign against government agencies, without attributing it to China.
Developers
- Peter Steinberger
- Nous Research
- Large language model developers
- AI agent system developers
Deployers
- Threat actors
- hackers
- China-linked threat actors
- AI agent system deployers
- Agentic threat actors
Harmed parties
- Taiwanese government employees
- Taiwanese government agencies
- Taiwan Ministry of Justice
- Privacy
- National security and intelligence stakeholders
- Information security
- Governments
- Government of Taiwan
- Government agencies
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: AI agents were used to compromise government systems and exfiltrate sensitive data, constituting a significant security incident.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8