What’s Vulnerable › Vulnerabilities

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

• Severity: high (CVSS 8.6 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.3% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-04-01 · updated 2026-06-17
• Weakness: CWE-20

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.

Affected products

• onnx: before 1.21.0 — fixed in 1.21.0

How to fix

Upgrade to a fixed version: onnx 1.21.0. Check the vendor advisory for mitigations.

References

• https://github.com/onnx/onnx/commit/e30c6935d67cc3eca2fa284e37248e7c0036c46b
• https://github.com/onnx/onnx/pull/7751
• https://github.com/onnx/onnx/security/advisories/GHSA-538c-55jv-c5g9

Get alerted when CVE-2026-34445 or the next vulnerability affects your stack