bleeping-computer · Crawled Nov 21, 2026

Hackers use autonomous AI tool Cairn to find zero-day, take over server

2 IoCs
Read original article ↗

AI Summary

A Chinese-nexus threat actor used an autonomous AI tool called Cairn to discover and exploit a zero-day vulnerability in the open-source medical imaging application MONAI Label. The AI agents were instructed to obtain shell access, autonomously identified a path traversal flaw, and exploited it to write a Python reverse shell to the sitecustomize.py file, achieving root access on the server. The campaign targeted East Asian educational institutions between September 8 and 10, 2026, with attack infrastructure linked to two public IP addresses. Amazon reported the vulnerability to the maintainers, who released a patch on November 18, 2026.

AI-extracted · verify before operational use

Indicators of Compromise 2 extracted

Type Value Detail
IP 142[.]4[.]98[.]145 Details →
IP 142[.]4[.]107[.]34 Details →