Threat Intelligence Database

Tract is a tiny, no-nonsense, self-contained TensorFlow and ONNX inference toolkit. Prior to 0.21.16, 0.22.2, and 0.23.1, tract-nnef uses unchecked usize multiplication in nnef/src/tensors.rs read_tensor for attacker-controlled tensor dimensions, the allocation size, and the reported tensor length. Loading a crafted NNEF archive through model_for_path or model_for_read reaches the default DatLoader and can make the wrapped size check accept a small allocation while data/src/tensor.rs as_slice_unchecked creates a much larger logical slice. Model construction through as_uniform can then read beyond the heap allocation and disclose adjacent data, and later access can terminate the process with a segmentation fault. The affected dense numeric tensor path does not include the independently guarded bool, String, or block-quant paths, and no out-of-bounds write or code execution was demonstrated. This issue is fixed in versions 0.21.16, 0.22.2, and 0.23.1.

CVE-2026-75093 is a medium severity vulnerability in sonos tract up to version 0.23.4. It involves an incorrect calculation of buffer size in the function Tensor::from_raw_dt_align within the ONNX Initializer Loader component. The vulnerability can be exploited remotely and requires user interaction. A patch identified by commit 66b10bda8895f4bfaf8c205361f0125cdf51f99b is available to fix this issue.