Paper/Archive/CVE-2026-48705

CVE-2026-48705

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

public exploit CVSS 9.3

critical.is priorityof 100

CVSS 9.3 (CNA)9.3 / 10 × 3027.9 Not in CISA KEV+300.0 No EPSS score.000 × 200.0 Exploit: SSVC poc+1010.0 SSVC exploitation: poc+100.0

Description · from the CVE record

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

ProductAffectedFixed inSource

MONAI< 1.6.1–CNA

Scores by source

GitHub_M (CNA)9.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:N/I:H/A:L

CISA ADPSSVCExploitation: poc · Automatable: yes · Technical impact: partial

References

exploitgithub.com/Project-MONAI/MONAI/security/advisories/GHSA-6hp3-vr39-rqw8 refgithub.com/Project-MONAI/MONAI/pull/9087 refgithub.com/Project-MONAI/MONAI/commit/434c094a3e6b84cca5b6e81da51e0d18a0100607 refgithub.com/Project-MONAI/MONAI/releases/tag/1.6.1