AI Agents Exploit MONAI Label Zero-Day in China-Linked Hack
🤖 Amazon reports that autonomous AI agents operated by a China-linked threat actor discovered and exploited a zero-day flaw in MONAI Label, an open source medical imaging annotation tool. The agents moved from API mapping to arbitrary file writes in about 11 minutes, ultimately gaining a root shell. Targets were universities in East Asia outside mainland China. A critical advisory now covers versions 0.8.5 and earlier.
