CVE-2026-73325

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.

Published 12 Aug 2026, 16:17 UTC Last modified 12 Aug 2026, 16:17 UTC

8.4

CVSS 4.0 HIGH base score

CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Attack profile

The conditions required to exploit this vulnerability and its potential impact.

Attack vector Local

Attack complexity Low

Privileges required None

User interaction Active

Scope Not assessed

Confidentiality Not assessed

Integrity Not assessed

Availability Not assessed

Affected products

Product applicability statements supplied with the NVD record.

NVD has not published structured affected-product data for this record.

Weakness classification

CWE categories help security teams group the underlying software weakness.

CWECWE-502

Source references

External advisories, patches and technical reports attached to this CVE record.

NVD National Vulnerability Database recordnvd.nist.gov 01 Technical reference disclosure@vulncheck.com 02 Technical reference disclosure@vulncheck.com 03 Technical reference disclosure@vulncheck.com