Jul 1, 2026Confirmed
Hackers reportedly used AI agents to breach Taiwanese government systems and take personnel records
Rogue: Caused harmAI loose in the worldData exfiltrationDERIVED
Approved by person, Oct 11, 2026. How entries are approved
From July 1–4, 2026, suspected China-linked hackers reportedly used a multi-agent framework built on Hermes and OpenClaw against Taiwanese government systems. The agents reportedly compromised 85 credentials and exfiltrated more than 2,564 personnel records. Taiwan confirmed an overseas AI-assisted campaign without attributing it to China.
What this means for youAI agents are reportedly being used to run break-ins against government networks with little human effort. Governments should expect faster, automated attacks on stolen logins. Households and small businesses can use unique passwords and turn on two-step sign-in so one stolen credential does not open other systems.
Sources
- AI Incident Databasehttps://incidentdatabase.ai/cite/1646
Data from the AI Incident Database (incidentdatabase.ai), licensed CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/). McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. IAAI-21.
Source data license: CC BY-SA 4.0 (database). Report contents keep their own rights; reports.text, submissions, images and videos are excluded from the data license.
rogue:R4
Covered by snapshot 45
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
This entry is record number 2107. It has not been edited since it was approved; the hash above would not match if it had. How to verify