CVE-2026-109361
Received Received - Intake

Insecure Deserialization in MONAI nnUNetV2Runner

Publication date: 2026-10-12

Last updated on: 2026-10-12

Assigner: VulnCheck

Description
MONAI 1.2.0 before 1.6.1 contains an insecure deserialization vulnerability in nnUNetV2Runner that unpickles the postprocessing_file path read from inference_information.json without confining it to the results directory. Attackers who can modify inference_information.json can point it at a malicious pickle elsewhere on the filesystem to execute code when predict_ensemble_postprocessing runs.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-10-12
Last Modified
2026-10-12
Generated
2026-10-12
AI Q&A
2026-10-12
EPSS Evaluated
N/A
NVD
CVE-2026-109361
EUVD
EUVD-2026-97663

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
Project-MONAI MONAI 1.2.0

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-502 The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability is an insecure deserialization flaw in MONAI 1.2.0 through 1.6.0 affecting the nnUNetV2Runner component. Attackers who can modify inference_information.json can set the postprocessing_file path to a malicious pickle file outside the results directory. When predict_ensemble_postprocessing runs, it unpickles and executes code from this file, leading to remote code execution.

Detection Guidance

Check for MONAI versions between 1.2.0 and 1.6.0 using pip show MONAI or pip list. Inspect inference_information.json files for suspicious postprocessing_file paths pointing outside the results directory. Look for unexpected pickle files in system directories.

Impact Analysis

If you use MONAI versions 1.2.0 to 1.6.0 and an attacker can modify inference_information.json, they could execute arbitrary code on your system with the privileges of the user running the MONAI process. This could lead to data theft, system compromise, or further network infiltration depending on your environment.

Compliance Impact

This vulnerability could lead to unauthorized code execution, potentially violating data confidentiality and integrity requirements in GDPR and HIPAA. If exploited, it may result in unauthorized access to protected health information or personal data, triggering compliance violations and regulatory penalties.

Mitigation Strategies

Upgrade MONAI to version 1.6.1 or later immediately. Remove write access to inference_information.json files for untrusted users. Validate all postprocessing_file paths are confined to the results directory. Set MONAI_ALLOW_PICKLE=0 if available in your version.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-109361. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart