## ONNX: Out-of-Bounds Read in RNN/GRU/LSTM Shape Inference (Old Opsets, Missing Rank Check)

- 種別: advisory
- 重大度: medium
- 関連技術: python
- CVE: CVE-2026-115919
- 公開日時: 2026-10-28T21:16:24.000Z
- 情報源: GitHub Advisory Database (https://github.com/advisories/GHSA-48m4-24cq-37qf)
- パーマリンク: https://vulnpulse.app/items/ghsa-ghsa-48m4-24cq-37qf

影響: pip:onnx <= 1.21.0 → 1.22.0
ONNX shape inference performed an out-of-bounds read when processing a malformed RNN, GRU, or LSTM node from opsets 1–6 whose first input had a rank other than three. RNNShapeInference_opset1_to_6() checked whether the input shape was present but accessed dim(0) and dim(1) without first checking its rank. A crafted model could therefore terminate a process that called onnx.shape_inference.infer_shapes(). The model passed onnx.checker.check_model() before reaching the vulnerable path. Technical…