CVE-2026-73325
HighCVSS 7.8Exploitation Probability (EPSS)
Low risk17th percentile - higher than 17% of all known CVEs
Summary
Fujitsu Research's OneCompression library before 1.2.1 contains an unsafe deserialization vulnerability that allows attackers to execute arbitrary code by supplying a crafted model.pt checkpoint file. The load_quantized_model_pt() function unconditionally calls torch.load with weights_only=False, invoking Python's pickle machinery during deserialization.
Risk Assessment
Attackers can execute arbitrary Python code, including system commands, when loading a model file, potentially leading to system compromise.
Recommendation
Update the OneCompression library to version 1.2.1 or later. Avoid loading models from untrusted sources.
Original NVD description (English source)
Fujitsu Research's OneCompression library before 1.2.1 contains an unsafe deserialization vulnerability that allows attackers to execute arbitrary code by supplying a crafted model.pt checkpoint file, as QuantizedModelLoader.load_quantized_model_pt() unconditionally calls torch.load with weights_only=False, invoking Python's pickle machinery during deserialization. Attackers can embed malicious __reduce__ methods in a crafted model checkpoint to execute arbitrary Python code, including system commands, when the library loads the file from a caller-selected model directory.