CVE-2026-115919
MEDIUM
MEDIUM
Priority: 0.01
BB Relevance:
47/100
Published: 2026-10-26
Modified: 2026-10-26
First seen: 2026-10-29
Status: active
Attack Surface
Low Complexity
No Auth
No Interaction
CVSS Vector Breakdown
AV:
Local
AC:
Low
PR:
None
UI:
None
S:
Unchanged
C:
None
I:
None
A:
High
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.