Hackers use autonomous AI tool Cairn to find zero-day, take over server
Threat actors used the open-source AI penetration-testing framework Cairn to find a previously unknown vulnerability in a medical imaging application. [...]
Hackers use autonomous AI tool Cairn to find zero-day, take over server
Bill Toulas
- November 20, 2026
- 12:30 PM

Hackers used an autonomous AI agent platform called "Cairn" to discover a zero-day vulnerability in a medical imaging application and exploit it to take complete control of a server.
According to Amazon Threat Intelligence, the suspected Chinese-linked attackers simply instructed the AI agents to "obtain shell access," leaving them to independently discover and exploit the flaw.
Amazon Threat Intelligence uncovered the campaign after discovering that the attackers had left their Cairn instance publicly accessible without authentication, exposing their hacking operations.
According to the researchers, the attacks were launched by a Chinese-nexus threat actor between September 8 and 10, 2026, targeting mainly East Asian educational institutions outside China.
Cairn is a legitimate pentesting tool that can be used to coordinate multiple AI agents in cyber-operations, created for research and defense strengthening.
Gambit Security documented cases of Cairn abuse as part of a large-scale credit card stealing operation in September. More recently, Google reported it was deployed in an attack against an aerospace organization in the U.S.
During the campaign investigated by Amazon, the AI agents were not always successful. For example, a 16-hour and 148-action effort to take control of a Redis server failed.
In a separate case targeting a university GPU server, the agents tried over 30,000 credential combinations over six hours but failed to brute-force their way in.
Finding and using a zero-day
According to Amazon, Cairn's AI agents found a path traversal zero-day in MONAI Label, an open-source medical imaging application that uses AI to help researchers label medical images.
The flaw enabled the agents to write files to arbitrary locations on the server, and within 11 minutes, they went from mapping the application's API to exploiting the vulnerability.
In a subsequent session, the AI agents used the flaw to write a Python reverse shell to theΒ sitecustomize.py file that automatically loads when Python starts, then triggered an API endpoint to establish root access to the server.
After discovering the zero-day, the operator provided the agents with a proxy into a second university network running the same vulnerable software and directed them to target other machines.
Amazon reported the flaw to MONAI Label maintainers, and they released a security update to address it on November 18.
The researchers attributed the campaign to a Chinese-nexus threat actor with moderate confidence, based on the language of the retrieved prompts, the activity timestamps, and the choice of targets.
Amazon also shared two IP addresses associated with the campaign, observed between September 8 and 10, 2026:
- 142[.]4.98.145
- 142[.]4.107.34
Amazon warned that AI agents can find and exploit vulnerabilities faster than security teams can react, urging organizations to rely more on automated defenses rather than manual investigations.
Uncover email threats your existing defenses may miss.
Adaptive Security's AI agents analyze email intent, context, and behavior to uncover phishing, business email compromise, and invoice fraud.
See what's getting through with a 14-day read-only scan of Microsoft 365 or Google Workspace, with no MX changes.
Start your free email security scan.Originally published by BleepingComputer. Aggregated on AIWithGhost for educational purposes β full credit and traffic to the original publisher.
