Attackers' AI agents independently discovered a zero-day in MONAI Label, an open-source medical imaging AI application, and used it to write files outside the intended storage directory in about 11 minutes, Amazon said Friday. The fix has been merged into the source code, but no patched release is available.
Amazon assesses with high confidence that the flaw was a zero-day because it found no prior fix, issue, advisory or mention in vulnerability databases at the time of discovery.
Amazon found the attackers' Cairn server Sept. 10 running without authentication and read the operator's prompts. Cairn is an open-source framework that coordinates AI agents for security testing. The campaign ran about 48 hours from Sept. 8 against universities in East Asia outside mainland China, and Amazon assesses a China nexus with moderate confidence.
The operator gave the agents one goal, "obtain shell access." On MONAI Label, the agents discovered they could manipulate a file-upload feature to place files outside the application's intended storage area. In a later session, they exploited the same flaw to run malicious code and gain full control of the server.
MONAI Label's fix has waited for a release since Oct. 19
MONAI Label's maintainers published a critical GitHub security advisory on Wednesday. It lists no patched version for 0.8.5 and earlier and says the fix "will be included in the next MONAI Label release." The fix was merged into the project's main branch on Oct. 19 in pull request #1915. MONAI Label’s newest release on the Python Package Index (PyPI) is still 0.8.5, uploaded Nov. 25, 2024.
Authentication is disabled by default, the advisory says, meaning anyone who can reach the server can exploit the vulnerability. Even with authentication enabled, users assigned the ANNOTATOR role can still exploit it.
What MONAI Label teams can do now
With no patched release available, administrators should identify MONAI Label servers running version 0.8.5 or earlier. The security advisory recommends three workarounds:
Enable authentication and restrict the ANNOTATOR role to trusted users.
Keep MONAI Label servers off untrusted networks.
Run the software without administrator privileges and limit its ability to write files outside its designated storage directory.
Once a release containing the fix becomes available, administrators should upgrade.
Because Amazon documented attackers exploiting the flaw, administrators should also check for signs that their servers have already been compromised, including unexpected changes to application files. Enabling authentication now won't undo an earlier intrusion.
