Coding & agents New
Amazon says a Chinese-linked group's AI agents found a zero-day on their own and used it to take over a university server
Published:
Amazon Threat Intelligence published findings on Friday about a threat actor that ran Cairn, an open-source autonomous penetration-testing framework, against universities in East Asia outside mainland China over about 48 hours from 8 September. The actor gave the agents goals such as 'obtain shell access' and let them plan and adjust without choosing each step.
Against an open-source medical imaging AI application, the agents found a path-traversal flaw and went from mapping the API to writing files on the server in about 11 minutes. In a later session they used it to plant a Python payload and obtain a reverse shell running as root. The Register identifies the software as MONAI Label; Amazon says the maintainers have released a fix and a GitHub security advisory.
Other operations failed: one ran about 16 hours and 148 sequential actions against an open Redis server, another tested more than 30,000 credential combinations. Amazon found the campaign because the operator left the Cairn server publicly accessible without authentication.
Caveat. Amazon's attribution to a Chinese-linked actor is its own assessment, made with moderate confidence, based on Simplified Chinese prompts, China Standard Time timestamps and the choice of targets.
Sources