Back to CVE records
Low 3.3Published Aug 18, 2026

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

Updated under an hour ago ()

Does this affect you?

It affects onnx. Add what you run to find out whether that includes you.

No exploitation reported and no EPSS estimate yet.

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.

CVSS
3.3 LOW (v3.1, CNA)CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:L
Weakness (CWE)
CWE-125
Known exploited
Not in CISA's KEV catalog
EPSS (exploitation in the next 30 days)
Not loaded for this CVE
Assigned by
GitHub_M
NVD analysis
Awaiting Analysis
Record last updated
Aug 18, 2026
First seen by InfoSec Signals
Oct 9, 2026

Affected products

Affected products
onnx onnx
onnx:onnx (from the name)
from 1.3.0, < 1.22.0
CNA record

References

  • x-refsource-confirm
  • x-refsource-misc
  • x-refsource-misc
  • x-refsource-misc

The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.

Your cookie choices
We use essential cookies to run this site, and, only with your consent, an advertising cookie from Google to measure whether our ads lead to sign-ups and subscriptions. See our for details.