theregister.com·20 november 2026

China attackers deployed AI agents that autonomously found and exploited a 0-day to take over a university server

Image for the article: China attackers deployed AI agents that autonomously found and exploited a 0-day to take over a university server
Image via theregister.com

Suspected Chinese spies deployed AI agents that autonomously found and exploited a zero-day vulnerability in the open-source medical imaging AI application MONAI Label, gaining full control of a university server. The agents, using the Cairn penetration-testing framework, adapted for nearly a full day without human direction. Amazon's Threat Intelligence Team discovered the campaign targeting universities in East Asia. The campaign also involved failed attempts to exploit other vulnerabilities, including Log4Shell and SSRF attacks. This highlights the growing use of autonomous AI agents in both espionage and criminal operations.