MONAI: MONAILabel Server Crash and Silent Inference Corruption via Crafted DICOM (pydicom DS/IS Validation Bypass)
MONAI up to 1.5.2 is affected when MONAILabel runs its default REST API with no authentication configured. The advisory lists 1.6.1 as the patched version.
Written by anthropic/claude-haiku-5.5 from the sources below. Verify against them.
- Exploited
- Proof of concept public, per CISA
- Fix
- Fixed in 1.6.1
- Who is exposed
- Default setups
Do first: Check every install: default setups are affected.
- Last modified
- A 0-100 score for how much a CVE matters across the industry: exploitation, exposure, how widely the software is used, severity and whether a fix exists.What do these mean? →
- 59/100 · provisional
- How many real-world setups can hit the bug, from the vendor's advisory and CISA data. It does not know your setup.What do these mean? →
- Default setups
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
- Exploitation: poc
- Automatable: yes
- Technical impact: partial
Summary
An unauthenticated attacker can reach MONAI's MONAILabel server remotely by uploading a crafted DICOM file, which can crash inference or silently corrupt stored and output image data. The flaw is in how the software handles non-finite values in DICOM spatial fields, and the attack works against a default deployment.
Read the original 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.
cve.now Index
- Exploitation15/40CISA rates a proof of concept as public
- Exposure25/25Default setups, CISA rates it automatable
- Reach10/20Affects PyPI packages
- Severity9.3/10CVSS 9.3
- No patch0/5No signal
What would change the score
- Would score about 84 if added to CISA KEV
- Would score about 79 if CISA's SSVC rates exploitation active
Impact
- Widely used
monai has 90.3k weekly downloads.Source: pypistats.org
128 packages depend on monai.Source: deps.dev
What to do
Check every install: default setups are affected.
Upgrade to a fixed version: 1.6.1.
Timeline
- CVE published
- First seen by cve.now
- Posted on X by cve.now
- CISA SSVC assessment
Exploitation: poc · Automatable: yes · Technical impact: partial
- Record last updated
Affected versions
- Project-MONAI MONAI
fixed in 1.6.1
- monaiPyPI
fixed in 1.6.1
Evidence 4
- Advisory
- Repository
- Repository
- Repository
Corrections
None so far.
Something wrong on this page? Report an error. Every fix is listed here.
Questions about CVE-2026-48705
Is CVE-2026-48705 being exploited?
It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. CISA's SSVC assessment notes a proof of concept exists. No public exploit code is tracked.Source: cve.now feed data
What does this mean?
A single crafted DICOM upload of about 132 KB can crash the MONAILabel inference pipeline. The same upload can also silently corrupt segmentation results and leave a poisoned DICOM in the datastore. The root issue is a validation bypass in how DS and IS values are handled by pydicom.Source: github.com
Which versions are affected by CVE-2026-48705?
MONAI: before 1.6.1. monai (PyPI): before 1.6.1.Source: cve.now feed data
Am I affected, and how do I check?
MONAI versions up to 1.5.2 are listed as affected, and the advisory lists 1.6.1 as the patched version. The relevant setup is a MONAILabel server running its default REST API with no authentication configured. To check, look at the installed MONAI version (for example with pip show monai) and at whether the MONAILabel server has authentication configured.Source: github.com
How do I fix CVE-2026-48705?
Upgrade MONAI to 1.6.1 or later. The facts provided do not describe a workaround, so none is given here.Source: github.com