Live › vulnerability › CVE-2026-115921
Go to dashboardONNX, an open machine learning model format library, mishandles the num_scan_inputs attribute in its Scan inference functions. A crafted model with that attribute missing or negative can crash or disrupt shape inference when loaded.
Summary written from the sources below. Check the originals before acting.
First seen by InfraStack 2026-10-26 18:31 UTC. All times on this page are UTC.
Applications that load or run ONNX models supplied from outside the team, such as user uploads or third-party model files, are exposed to a denial-of-service crash. Teams that only load their own trusted models, or that do not use ONNX, can skip it.
No product ranges from the sources yet.
python -c "import onnx; print(onnx.__version__)"; versions from 1.4.0 up to but not including 1.22.0 are affected1.22.0 or laterEach row is the first time that source carried this signal. The analyst’s rows are its own findings.
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.4.0 until 1.22.0, ScanInferenceFunction, ScanInferenceFunction_opset8, and ScanInferenceFunction_opset9 do not safely validate the required num_scan_inputs attribute. A missing attribute is dereferenced as a null pointer, while a negative value is converted to size_t and can reach an exceptional oversized allocation path. An untrusted model can therefore terminate or disrupt shape inference, including a negative-value model that can pass onnx.checker.check_model(). This issue is fixed in version 1.22.0.
This page as .md · .json · in your agent: get_signal("CVE-2026-115921")
NVD data is provided by NIST and is public domain. Posts quoted belong to their authors.