CVE-2026-34445

HIGH

ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.

Title source: cna

Description

Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to version 1.21.0, the ExternalDataInfo class in ONNX was using Python’s setattr() function to load metadata (like file paths or data lengths) directly from an ONNX model file. It didn’t check if the "keys" in the file were valid. Due to this, an attacker could craft a malicious model that overwrites internal object properties. This issue has been patched in version 1.21.0.

Scores

CVSS v3 8.6
EPSS 0.0019
EPSS Percentile 40.6%
Attack Vector NETWORK
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H

CISA SSVC

Vulnrichment
Exploitation none
Automatable yes
Technical Impact partial

Details

CWE
CWE-20 CWE-400 CWE-915
Status published
Products (3)
linuxfoundation/onnx < 1.21.0
onnx/onnx < 1.21.0
pypi/onnx 0 - 1.21.0PyPI
Published Apr 01, 2026
Tracked Since Apr 01, 2026