Amazon says a suspected Chinese-nexus actor's Cairn AI agents found and exploited a zero-day in an open-source medical imaging AI application on their own, getting a root shell on a university server
Amazon Threat Intelligence said in an AWS Security Blog post by CJ Moses dated 20 November 2026 that on September 10, 2026 it found a publicly hosted instance of Cairn, an open-source autonomous AI penetration-testing framework, running without authentication, and that its history showed a campaign targeting IP addresses associated with universities in East Asia outside mainland China over about 48 hours beginning September 8, 2026 (source: AWS).
Amazon says the operator gave the agents variations of the goal "obtain shell access"; against an open-source medical imaging AI application the agents found a path traversal flaw in an upload endpoint's filename parameter, went from mapping the application's API to arbitrarily writing files on the server in about 11 minutes, and in a later session wrote a Python reverse shell to sitecustomize.py and triggered a training API endpoint to get a reverse shell running as root; Amazon assesses with high confidence that the flaw was a zero-day (source: AWS).
Amazon says other operations failed, including about 16 hours and 148 sequential actions against an unauthenticated Redis instance and more than 30,000 credential combinations against a university GPU server and other systems; it assesses with moderate confidence that the actor is Chinese-nexus, based on Simplified Chinese prompts, China Standard Time script timestamps and the targeting (source: AWS).
Amazon says it notified the project's maintainers, who released a fix and a GitHub Security Advisory, that the affected organisations were not AWS customers and AWS worked with a government partner to notify them, and it published two IP addresses seen in records dated September 8 to 10, 2026: 142[.]4.98.145 and 142[.]4.107.34 (source: AWS).
BleepingComputer names the affected application as MONAI Label and says its maintainers released a security update on November 18 (source: BleepingComputer).
- Product
- Cairn open-source autonomous AI penetration-testing framework (abused by the actor); target: an open-source medical imaging AI application (MONAI Label, per BleepingComputer)
- Versions
- n/a — threat activity report; Amazon lists no affected versions
- Exploited in Australia?
- unknown
- Patch to
- Amazon advises prioritising high-confidence detections that trigger automated response, with humans overseeing outcomes; check logs for the two IP addresses Amazon published. MONAI Label users: apply the maintainers' 18 November security update (per BleepingComputer).
- Primary: AWS Security Blog — Chinese-nexus actor’s Cairn AI agents found a zero-day on their own (CJ Moses, 20 Nov 2026)
- Source: BleepingComputer — Hackers use autonomous AI tool Cairn to find zero-day, take over server (Bill Toulas, November 20, 2026)
- Source: The Record — Amazon says Chinese hackers used Cairn AI tool to discover apparent zero-day during attack on university (Jonathan Greig, November 20th, 2026)
