Amazon: AI agents exploited a MONAI Label zero-day
According to SecurityWeek, AI agents found and exploited a zero-day in MONAI Label, and Amazon assesses with moderate confidence that the actor is Chinese-nexus.
Amazon Threat Intelligence identified a server with a publicly hosted instance of Cairn, an open-source autonomous artificial intelligence (AI) penetration-testing framework, running without authentication on September 10, 2026. Analysis of that instance revealed a campaign targeting Internet Protocol (IP) addresses associated with universities in East Asia outside mainland China over approximately 48 hours beginning September 8, 2026. According to SecurityWeek, the AI agents found and exploited a zero-day path traversal vulnerability in MONAI Label, an open-source medical imaging AI application.
Amazon assesses with high confidence that the flaw was a zero-day based on the absence of any corresponding fix, issue, advisory, or prior mention in vulnerability databases for the affected project. The report says the vulnerability affects versions 0.8.5 and earlier. The actor also provided the agents a proxy that tunneled into a second university network running the same vulnerable software.
Why it matters in production
The agents went from mapping the application’s application programming interface (API) to arbitrarily writing files on the server in about 11 minutes. They used the vulnerability to write a Python reverse shell payload to sitecustomize.py and established a reverse shell running as root. Amazon assesses with moderate confidence that the actor is Chinese-nexus. The operator wrote prompts in Simplified Chinese, and timestamps in executed scripts were configured to China Standard Time.
One operation ran 148 sequential actions over roughly 16 hours against an unauthenticated Redis instance and failed. They also tested more than 30,000 credential combinations against a university graphics processing unit (GPU) server’s Secure Shell (SSH) and never found a working login.
What to do
Apply the fixed release and follow the GitHub Security Advisory that the maintainers released after notification.
Sources
Related reading
3 postsDiscussion
Spotted an error? Send corrections to [email protected] .