Vulnerability · Published Nov 5, 2026 · Assigned by GitHub_M

CVE-2026-48705MONAI: MONAILabel Server Crash and Silent Inference Corruption via Crafted DICOM (pydicom DS/IS Validation Bypass)

Critical 9.3

In plain English

A critical-severity improper input validation in MONAI from Project-MONAI. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 44% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)9.3Critical

Exploit odds (30 days)0.5%top 56.4% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	monai	1.6.1	GHSA-6hp3-vr39-rqw8

Affected products (as reported)

Vendor	Product	Versions
Project-MONAI	MONAI	< 1.6.1

Weakness: CWE-20, CWE-682 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:N/I:H/A:L

References

https://github.com/Project-MONAI/MONAI/security/advisories/GHSA-6hp3-vr39-rqw8 x_refsource_CONFIRM
https://github.com/Project-MONAI/MONAI/pull/9087 x_refsource_MISC
https://github.com/Project-MONAI/MONAI/commit/434c094a3e6b84cca5b6e81da51e0d18a0100607 x_refsource_MISC
https://github.com/Project-MONAI/MONAI/releases/tag/1.6.1 x_refsource_MISC