Skip to content
AI Agents Exploit MONAI Label Flaw in 11 Minutes

AI Agents Exploit MONAI Label Flaw in 11 Minutes

Wisevoter • November 21, 2026

Attackers' AI agents used an unpatched zero-day in the open-source medical imaging tool MONAI Label to gain control of servers.

Updated on Nov. 21, 2026 in Cybersecurity

Amazon reported that attackers' AI agents discovered and exploited a zero-day flaw in MONAI Label, writing files outside its intended storage directory in 11 minutes. MONAI Label's maintainers published a critical security advisory listing no patched version for 0.8.5 and earlier.

The campaign, which ran 48 hours against universities in East Asia outside mainland China, shows that autonomous AI agents can find and chain together vulnerabilities at machine speed. Authentication is disabled by default in MONAI Label, and users assigned the ANNOTATOR role can exploit the flaw even when authentication is enabled.

Attackers exploited a file-upload feature to place files outside the application's intended storage area, then used the same flaw in a later session to run malicious code and gain full control of the server. The fix was merged into the source code on Oct. 19 as pull request #1915, but it is not yet in a released version.

Amazon is a multinational technology company whose security team identified and reported the attack campaign and the exploitation of the MONAI Label flaw.

MONAI Label is an open-source medical imaging annotation tool built on the MONAI framework, widely used by researchers developing AI models for healthcare.

Amazon found the attackers' Cairn server running without authentication on Sept. 10. The operator gave the agents one goal, "obtain shell access," and the agents chained the file-upload flaw into remote code execution against universities in East Asia.

Nov. 25, 2024: MONAI Label version 0.8.5 uploaded to PyPI.

Nov. 25, 2024: MONAI Label version 0.8.5 uploaded to PyPI.

Sept. 8: Attack campaign against East Asian universities began.

Sept. 8: Attack campaign against East Asian universities began.

Sept. 10: Amazon found the attackers' Cairn server unauthenticated.

Sept. 10: Amazon found the attackers' Cairn server unauthenticated.

Oct. 19: Fix merged into the MONAI Label main branch.

Oct. 19: Fix merged into the MONAI Label main branch.

Nov. 21, 2026: Amazon publicly disclosed the exploitation; maintainers published the advisory.

Nov. 21, 2026: Amazon publicly disclosed the exploitation; maintainers published the advisory.

The case extends Amazon's reporting on AI-driven attacks by showing autonomous agents exploiting an open-source medical imaging tool within minutes, outpacing the patch cycle of its maintainers. It places pressure on defenders in a race where offensive automation is shrinking the window between disclosure and exploitation.

Researchers and institutions running MONAI Label versions 0.8.5 and earlier have no patched release available and face exposure if authentication is disabled or users hold the ANNOTATOR role. Until the fix ships in the release, restricting network access to the server and enabling authentication reduce the risk.

Machine-speed exploitation means that software operators should treat disabled-by-default authentication and unpatched open-source tools as immediate risks, not routine maintenance items.

Explore more Cybersecurity coverage on how attackers are using automation to exploit software flaws faster.

Source note: This article includes information reported by VentureBeat.

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

AI Agents Exploit Unpatched MONAI Label Path-Traversal Flaw to Gain Root on University Server 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. 2 sources 69

Extracted Entities