Amazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-Day
Amazon says autonomous AI agents run by a China-linked threat actor found and exploited a zero-day vulnerability in MONAI Label, an open-source tool designed for AI-assisted annotation of medical images.
The tech giant’s threat intelligence team detected the activity in September, after coming across an exposed instance of Cairn, an open-source AI penetration testing framework. The instance had no authentication, so anyone could see the operator’s prompts and the agents’ output.
The records showed a roughly 48-hour campaign against IP addresses belonging to universities in East Asia outside mainland China. The operator gave the agents a list of targets and told them to obtain shell access.
After identifying the software on one target and mapping its API, the agents discovered a path traversal bug in a file upload function.
"In about 11 minutes, the agents went from mapping the application’s API to arbitrarily writing files on the server," Amazon said.
In a later session, the agents used the flaw to plant a Python reverse shell in a file Python runs every time the interpreter starts, ultimately achieving a root shell.
"Amazon Threat Intelligence assesses with high confidence that it was a zero-day based on the absence of any corresponding fix, issue, advisory, or prior mention in vulnerability databases for the affected open-source project," the company said.
The operator then gave the agents a proxy that tunneled into a second university and instructed them to target other devices on its network.
"The server that the proxy connected to was running the same vulnerable software, and we infer the actor had used the zero-day to compromise it and establish the tunnel," Amazon noted.
The MONAI Label developers published an advisory this week. It rates the bug critical and says it affects versions 0.8.5 and earlier. Authentication is off by default, enabling anyone who can reach the server over the network to exploit the vulnerability. A fix has been created and will be included in the next release.
Amazon has attributed the attack to an unidentified Chinese-nexus threat actor with moderate confidence, based on the language used in the prompts, the time zone in the scripts, and the fact that the targeted universities are likely of strategic interest to China.


