What’s Vulnerable › Vulnerabilities

CVE-2026-63632: ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape

• Severity: low (CVSS 3.3 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.2% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-08-18 · updated 2026-09-18
• Weakness: CWE-125

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.

Affected products

• onnx: from 1.3.0, < 1.22.0

References

• https://github.com/onnx/onnx/commit/e9c74f596eaa0250f89e52a54160a25bbcb25b66
• https://github.com/onnx/onnx/pull/7880
• https://github.com/onnx/onnx/releases/tag/v1.22.0
• https://github.com/onnx/onnx/security/advisories/GHSA-p893-rvq9-2xf9
• https://github.com/onnx/onnx/security/advisories/GHSA-p893-rvq9-2xf9

Get alerted when CVE-2026-63632 or the next vulnerability affects your stack