CVE-2026-115919
ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check)
- State
- Published
- Severity
- 6.2 Medium
- Published
- Oct 26, 2026
- Updated
- Oct 26, 2026
- Reserved
- Oct 23, 2026
Description
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to 1.22.0, RNNShapeInference_opset1_to_6() processes malformed RNN and LSTM nodes from opsets 1 through 6 and GRU nodes from opsets 3 through 6 without verifying that the first input has rank three. The function accesses dim(0) and dim(1) on an undersized protobuf shape, which can read outside the intended repeated field and terminate an application when onnx.shape_inference.infer_shapes() processes an untrusted model that can pass onnx.checker.check_model(). This issue is fixed in version 1.22.0.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 6.2 Medium | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | GitHub_M |
Weaknesses
- CWE-125 Out-of-bounds Read
Affected Products
| Product | Versions |
|---|---|
onnxonnx |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.