CVE-2026-34445
HIGHONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.
Title source: cnaDescription
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