Urgent.News

What's breaking now, across thousands of outlets.

AI

China attackers deployed AI agents that autonomously found and exploited a 0-day to take over a university server

'Agents kept adapting for nearly a full day without human direction,' Amazon CISO said

China attackers deployed AI agents that autonomously found and exploited a 0-day to take over a university server

China-linked attackers utilized autonomous AI agents to discover and exploit a zero-day vulnerability in the MONAI Label application, allowing them to infiltrate university networks and gain full control of a server, according to Amazon's Chief Information Security Officer, CJ Moses. The attack, which took place over a span of 48 hours, began on September 8 and was detected by Amazon's Threat Intelligence Team on September 10.

The attackers, using the open-source penetration-testing framework Cairn, attempted to breach other university servers with various tactics such as Redis replication abuse, Log4Shell injection, server-side request forgery, and credential sprays. Despite failing these attempts, the AI agents successfully identified and exploited the path traversal vulnerability in MONAI Label after 11 minutes, executing a Python reverse shell as root.

This incident highlights the increasing adoption of autonomous AI agent frameworks in both espionage and criminal operations.

Written by urgent.news from The Register's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Other reports of this story

Every outlet that reported this, and when →

Read the original at theregister.com →

More in AI

More from Friday 20 November →