CVE-2026-115919 ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check)
- Exploited in the wild
- Not known
- Fix
- Available
What is CVE-2026-115919?
CVE-2026-115919 is a medium-severity vulnerability in onnx, published on 26 Oct 2026.
Official 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.
Weakness: CWE-125
Which versions are affected by CVE-2026-115919?
2 open source packages ship an affected version, including onnx.
| Package | Affected | Fixed in |
|---|---|---|
onnx PyPI | All versions | 1.22.0 |
onnx PyPI | All versions | 1.22.0 |
How do I fix CVE-2026-115919?
Upgrade onnx to 1.22.0 or later.
Is CVE-2026-115919 being exploited?
There is no known exploitation of CVE-2026-115919 in the wild and no public exploit code.
Sources
Also known as DEBIAN-CVE-2026-115919, ECHO-2333-cd68-5267, GHSA-48m4-24cq-37qf, UBUNTU-CVE-2026-115919.