Attackers' AI agents found a zero-day in medical-imaging software and gained root access
Suspected China-linked hackers used autonomous AI agents to exploit a previously unknown path-traversal flaw in MONAI Label 0.8.5 and earlier. The flaw enabled unauthenticated file writes outside the intended storage folder and was used to obtain root access on one university server. A fixed installable version was not available in the source text.
CERT24