CVE-2026-55093: 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, a toolkit for running machine learning models (TensorFlow and ONNX inference, which means executing pre-trained AI models), has a vulnerability in how it handles tensor dimensions (the sizes of data arrays). Before versions 0.21.16, 0.22.2, and 0.23.1, an attacker could craft a malicious model file that tricks Tract into allocating a small amount of memory while actually trying to access a much larger area, potentially exposing nearby data in memory or crashing the program.