CVE-2026-34445
ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.
8.6
HIGH
CVSS 3.1
EPSS 0.21%
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.
How to fix CVE-2026-34445
To remediate CVE-2026-34445, upgrade the affected package to a fixed version below.
- —no fix listed
- —upgrade to 1.21.0 or later
Is CVE-2026-34445 being exploited?
Low — EPSS is 0.2%, meaning exploitation activity has not been observed at scale.
Affected packages (2)
- from 0
- from 0, < 1.21.0
CVSS scores
| Source | Version | Severity | Vector |
|---|---|---|---|
| osv | CVSS 3.1 | HIGH8.6 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H |