Severity
8.6HIGHNVD
EPSS
0.1%
top 65.82%
CISA KEV
Not in KEV
Exploit
No known exploits
Timeline
PublishedApr 1
Latest updateApr 2

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.

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:HExploitability: 3.9 | Impact: 4.7

Affected Packages5 packages

🔴Vulnerability Details

4
OSV
CVE-2026-34445: (Open Neural Network Exchange (ONNX) is an open standard for machine le2026-04-02
OSV
CVE-2026-34445: Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability2026-04-01
GHSA
ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.2026-04-01
OSV
ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.2026-04-01

📋Vendor Advisories

3
Microsoft
ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.2026-04-02
Red Hat
ONNX: python: ONNX: Denial of Service and potential information disclosure via malicious model metadata2026-04-01
Debian
CVE-2026-34445: onnx - Open Neural Network Exchange (ONNX) is an open standard for machine learning int...2026

🕵️Threat Intelligence

1
Wiz
CVE-2026-34445 Impact, Exploitability, and Mitigation Steps | Wiz

💬Community

1
Bugzilla
CVE-2026-34445 ONNX: ONNX: Denial of Service and potential information disclosure via malicious model metadata2026-04-01