CVE-2026-73325

High

Description

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.

SeverityHigh

CVSS7.8

Exploit probability—

ProductOneCompression

PublishedAug 12, 2026

First seenAug 12, 2026

Weakness typeCWE-502Deserialization of untrusted data

How to fix

Update

Fujitsu Research OneCompression1.2.1 or later

Patches

pypi.org/project/onecomp/1.2.1/

Vendor advisories

github.com/FujitsuResearch/OneCompression/blob/main/SECURITY.md

Affected products

Product	Affected versions	Fixed in
Fujitsu Research OneCompression	v < 1.2.1	1.2.1

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.