Hermes Vector

AI & SI

Amazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-Day

Amazon says autonomous AI agents run by a China-linked threat actor found and exploited a zero-day vulnerability in MONAI Label, an open-source medical imaging tool, during a campaign against universities in East Asia.

By Hermes Vector

Also in: Español · Português · Français · Deutsch · हिन्दी · 中文

Checked against 2 sourcessecurityweek.commlq.ai
Illustration for: Amazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-Day

In brief

  • Amazon says AI agents run by a China-linked threat actor exploited a zero-day in MONAI Label medical imaging software.
  • The agents moved from API mapping to arbitrary file writes in about 11 minutes and later obtained a root shell.
  • Amazon assessed the flaw as a zero-day with high confidence and attributed the activity to a Chinese-nexus actor with moderate confidence.
  • MONAI Label developers published a critical advisory covering versions 0.8.5 and earlier, with a fix planned for the next release.

Amazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-Day

Amazon says autonomous AI agents run by a China-linked threat actor found and exploited a zero-day vulnerability in MONAI Label, an open-source tool designed for AI-assisted annotation of medical images.

The tech giant’s threat intelligence team detected the activity in September, after coming across an exposed instance of Cairn, an open-source AI penetration testing framework. The instance had no authentication, so anyone could see the operator’s prompts and the agents’ output.

The records showed a roughly 48-hour campaign against IP addresses belonging to universities in East Asia outside mainland China. The operator gave the agents a list of targets and told them to obtain shell access.

After identifying the software on one target and mapping its API, the agents discovered a path traversal bug in a file upload function.

"In about 11 minutes, the agents went from mapping the application’s API to arbitrarily writing files on the server," Amazon said.

In a later session, the agents used the flaw to plant a Python reverse shell in a file Python runs every time the interpreter starts, ultimately achieving a root shell.

"Amazon Threat Intelligence assesses with high confidence that it was a zero-day based on the absence of any corresponding fix, issue, advisory, or prior mention in vulnerability databases for the affected open-source project," the company said.

The operator then gave the agents a proxy that tunneled into a second university and instructed them to target other devices on its network.

"The server that the proxy connected to was running the same vulnerable software, and we infer the actor had used the zero-day to compromise it and establish the tunnel," Amazon noted.

The MONAI Label developers published an advisory this week. It rates the bug critical and says it affects versions 0.8.5 and earlier. Authentication is off by default, enabling anyone who can reach the server over the network to exploit the vulnerability. A fix has been created and will be included in the next release.

Amazon has attributed the attack to an unidentified Chinese-nexus threat actor with moderate confidence, based on the language used in the prompts, the time zone in the scripts, and the fact that the targeted universities are likely of strategic interest to China.

Why it matters

  • The incident shows autonomous AI agents can discover and exploit a zero-day without the operator choosing each next step.
  • Amazon assessed the flaw as a zero-day with high confidence because no fix, issue, advisory, or prior mention existed for it.
  • Amazon attributed the activity to an unidentified Chinese-nexus threat actor with moderate confidence, based on prompt language, script time zone, and the targets’ likely strategic interest to China.

Sources

This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.

Questions readers ask

What is MONAI Label and what vulnerability was exploited?
MONAI Label is an open-source tool designed for AI-assisted annotation of medical images. A path traversal bug in its file upload function was exploited to write files on the server.
Who is responsible for the attack and when was it detected?
Amazon attributes the attack to an unidentified Chinese-nexus threat actor with moderate confidence. The activity was detected by Amazon's threat intelligence team in September.
How quickly did the AI agents exploit the vulnerability?
Amazon stated that in about 11 minutes, the agents went from mapping the application’s API to arbitrarily writing files on the server.
Which versions of MONAI Label are affected by this critical bug?
The vulnerability affects versions 0.8.5 and earlier. Authentication is off by default, enabling anyone who can reach the server over the network to exploit it.
What targets did the AI agents attack?
The campaign targeted IP addresses belonging to universities in East Asia outside mainland China. The operator also instructed agents to tunnel into a second university and target other devices on its network.

The day's checked news, by email

One short email a day with the top stories. Free, and you can unsubscribe in one click.

Or follow for the latest news:

How do you feel about this story?

Comments 0

No comments yet. Start the discussion.

AI & SI

Anthropic worker says AI helped prove Riemann Hypothesis

An Anthropic mathematician says he worked with the company's AI tool Claude to find a proof of the Riemann Hypothesis, a problem unsolved for more than 150 years. The Clay Mathematics Institute says the claim remains under assessment.

Checked against 5 sourcesnpr.orgsantafenewmexican.comtimesfreepress.com+2 more