Skip to content
AI Agents Exploit Unpatched MONAI Label Path-Traversal Flaw to Gain Root on University Server

AI Agents Exploit Unpatched MONAI Label Path-Traversal Flaw to Gain Root on University Server

First seen 21 Nov 2026, 13:47 UTC • •

Article Content

Browse articles
ThreatCluster AI
ThreatCluster •November 21, 2026 at 13:47 UTC
  • •MONAI Label 0.8.5 and earlier contain a path-traversal flaw in file upload handling that allows unauthenticated file writes outside the storage folder in the default setup.
  • •No fixed release exists yet; a fix was merged into source code, so defenders should restrict network exposure and enable authentication.
  • •Amazon reports AI agents achieved file-write capability in about 11 minutes and later obtained root on one university server via a planted startup file.
  • •Amazon links the campaign to a China-linked actor with moderate confidence, without naming a group or confirming state involvement.
  • •A second university network running the same software is believed compromised but not confirmed.

Amazon Threat Intelligence reports that suspected China-linked attackers used autonomous AI agents, run through the open-source Cairn framework, to find and exploit a path-traversal flaw in MONAI Label, an open-source medical imaging labeling server. The flaw lets an unauthenticated attacker write files outside the server's storage folder and affects MONAI Label 0.8.5 and earlier in the default configuration, where authentication is off. Amazon says the agents reached file-write capability in roughly 11 minutes during a 48-hour campaign in September, and a later session used the flaw to plant a startup file that yielded root access on one university server. Amazon attributes the campaign to a China-linked actor with moderate confidence, citing Simplified Chinese prompts and China Standard Time settings, but has not tied it to a named group or government. Amazon believes a second university network running the same software was compromised in the same way but has not confirmed this. The discovery followed Amazon finding the operator's Cairn control panel exposed without a password on September 10. The maintainers have merged a fix into the source code, but no patched release is available yet. Per the articles, users with the ANNOTATOR role can exploit the flaw even when authentication is enabled. Until a fixed version ships, the articles recommend restricting network access to the server and enabling authentication.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Timeline

2026-09-10
Attacker Cairn control panel found exposed
Amazon found the operator's Cairn panel on the internet without a password, exposing agent task settings, prompts and run history.
Wisevoter
2026-10-19
Fix merged into MONAI Label main branch
Fix merged as pull request #1915 but not yet included in a released version.
Wisevoter
2026-11-20
CVE-2026-133968 published
Published with CVSS 9.8 CRITICAL rating; first public proof-of-concept reported on 2026-11-21.
2026-11-21
Amazon discloses exploitation; advisory published
Amazon publicly disclosed the campaign; maintainers published a security advisory listing no patched version for 0.8.5 and earlier.
The Hacker News

More articles in this cluster (2)

Following this threat?

Track Amazon and CVE-2026-133968 in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.

Free account · no card needed

Common questions

Which MONAI Label versions are affected?
Versions 0.8.5 and earlier are affected in the default setup, which runs with no login enabled. No patched release is available yet.
Is this being exploited?
Amazon Threat Intelligence reports exploitation by suspected China-linked attackers using AI agents, with root access obtained on one university server.
What should we do first?
Restrict network access to the MONAI Label server and enable authentication, and review the ANNOTATOR role since the articles say it can exploit the flaw even with authentication enabled.