HIGHVulnerability
Verified
Global

NVD HIGH: CVE-2026-73325 — Fujitsu Research's OneCompression library 1.2.0 contains an unsafe deserializati...

·Source: NIST NVD

Updated:

Executive Summary

Fujitsu Research's OneCompression library 1.2.0 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_

Analysis

Fujitsu Research's OneCompression library 1.2.0 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. CVSS Score: 7.8. Published: 2026-08-12T16:17:23.000.

Indicators of Compromise (1)

CVE (1)
CVE-2026-73325
Source Attribution

Originally published by NIST NVD on Aug 12, 2026. Verified by: NIST.

Related Threats