CVE-2026-48705: critical vulnerability in Project-MONAI MONAI
MONAI: MONAILabel Server Crash and Silent Inference Corruption via Crafted DICOM (pydicom DS/IS Validation Bypass)
Published
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
28Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 9.3epss 0.5%
MONAI (Medical Open Network for AI) is an AI toolkit for health care imaging. Prior to 1.6.1, PydicomReader._get_affine() trusts non-finite values in the DICOM PixelSpacing, ImagePositionPatient, and ImageOrientationPatient fields and composes them into an affine matrix without validation. An unauthenticated attacker who can upload a crafted DICOM to a default MONAILabel deployment can propagate NaN or infinity values through LoadImaged, Spacingd, model inference, and output writing, causing inference failures, persistent datastore poisoning, or geometrically corrupted results. This issue is fixed in version 1.6.1.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:N/I:H/A:L
Affected products
Project-MONAI · MONAIRelated CVEs — Project-MONAI MONAI
In the same product, most dangerous first.
CVE-2026-100844HIGHMONAI before 1.6.0 OS Command Injection via dataset_name_or_idEPSS 0.9%CVE-2025-58756HIGHMONAI's unsafe torch usage may lead to arbitrary code executionEPSS 0.8%CVE-2025-58757HIGHMONAI's unsafe use of Pickle deserialization may lead to RCEEPSS 0.6%CVE-2025-58755HIGHMONAI has path traversal issue that may lead to arbitrary file writesEPSS 0.6%CVE-2026-109360HIGHMONAI 0.4.0 before 1.6.1 RCE via SENet Pretrained Weights Over Plaintext HTTPEPSS 0.6%CVE-2026-119578HIGHMONAI 1.6.0 before 1.6.1 Code Execution via Auto3DSeg algo_from_json()EPSS 0.6%