Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.3.0 until 1.22.0, onnx.version_converter.convert_version() can perform an out-of-bounds read in Gemm_7_6::adapt_gemm_7_6() in onnx/version_converter/adapters/gemm_7_6.h when a Gemm node has input tensors with fewer than two dimensions because B_shape[1], A_shape[0], or A_shape[1] is accessed without a rank check, potentially causing a process crash during an opset 7 to 6 downgrade. This issue is fixed in version 1.22.0.
Advisories
Source ID Title
Github GHSA Github GHSA GHSA-p893-rvq9-2xf9 ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape
Fixes

Solution

No solution given by the vendor.


Workaround

No workaround given by the vendor.

History

Tue, 18 Aug 2026 15:15:00 +0000

Type Values Removed Values Added
Description Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.3.0 until 1.22.0, onnx.version_converter.convert_version() can perform an out-of-bounds read in Gemm_7_6::adapt_gemm_7_6() in onnx/version_converter/adapters/gemm_7_6.h when a Gemm node has input tensors with fewer than two dimensions because B_shape[1], A_shape[0], or A_shape[1] is accessed without a rank check, potentially causing a process crash during an opset 7 to 6 downgrade. This issue is fixed in version 1.22.0.
Title ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape
Weaknesses CWE-125
References
Metrics cvssV3_1

{'score': 3.3, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:L'}


Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-08-18T14:55:15.923Z

Reserved: 2026-07-17T14:11:15.482Z

Link: CVE-2026-63632

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-08-18T15:16:56.463

Modified: 2026-08-18T15:16:56.463

Link: CVE-2026-63632

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses