Answer in brief
CVE-2026-63632 records a Low severity (CVSS 3.3) vulnerability in ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape. The current sources do not mark it as known exploited. The current feed maps onnx/onnx (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 3.3. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps onnx/onnx (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| onnx/onnxgeneric | >=1.3.0 <1.22.0 | 1.22.0 |
Published upstream
Aug 18, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 18, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 18, 2026
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.
Quoted source text, attributed separately from HOL analysis.