AI Incident Database #1646 · 2026-07-01
Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records
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.
- Risk class (MIT)
- Not yet classified
- Reports
- 4
- Developers and deployers named
- 9
Reports
- Taiwan says it was hit by ‘abnormal’ AI-assisted cyber-attack · theguardian.com, 2026-08-13
- Researchers observe first ‘near-autonomous’ AI attack on government target in Taiwan · cyberscoop.com, 2026-08-12
- Inside a Multi-Agent AI Framework Used to Compromise Government Entities in Asia · dreamgroup.com, 2026-08-12
- Taiwan says it was targeted last month in AI-driven hacking campaign · reuters.com, 2026-08-12
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.