Skip to main content
NewsPublished

Amazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-Day

Source SecurityWeek

0

Description

A China-linked threat actor used autonomous AI agents to discover and exploit a zero-day vulnerability in MONAI Label, an open-source medical image annotation tool. The vulnerability is a critical path traversal bug in a file upload function, allowing arbitrary file writes and remote code execution. The attack targeted universities in East Asia outside mainland China and achieved root shell access. MONAI Label versions 0.8.5 and earlier are affected, with authentication off by default. A fix has been created and will be included in the next release.

References

Community reviews

Loading reviews…