thehackernews.com·21 november 2026
Attackers' AI Agents Found a Zero-Day in Medical-Imaging Software and Gained Root Access

AI agents
Amazon Threat Intelligence
automated penetration testing
autonomous AI agents
China-linked hackers
critical severity
CVE-2026-133968
medical imaging
MONAI Label
open-source
path-traversal
path-traversal flaw
root access
university server
thehackernews.com
Suspected China-linked hackers exploited a path-traversal flaw in MONAI Label 0.8.5 and earlier to gain root access to a university server. The flaw allows unauthenticated attackers to write files outside the server's storage folder. The maintainers have merged a fix but have not released a patched version. Amazon Threat Intelligence reconstructed the intrusion, noting that autonomous AI agents mapped the application's interface and exploited the flaw within 11 minutes. The flaw is now listed as CVE-2026-133968 with a critical severity rating of 9.8.

