Vulnerability · Published Aug 12, 2026 · Assigned by VulnCheck

CVE-2026-73325Fujitsu OneCompression < 1.2.1 Arbitrary Code Execution via torch.load Deserialization

High 7.8

In plain English

A high-severity unsafe deserialization in OneCompression from Fujitsu Research. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 34% of all known vulnerabilities).

Severity (CVSS 3.1)7.8High

Exploit odds (30 days)0.4%top 65.6% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
Fujitsu Research	OneCompression	0 – before 1.2.1

Weakness: CWE-502 · Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References

Maintainer SECURITY.md vendor-advisory
Project Repository product
Patch Release patch
https://www.vulncheck.com/advisories/fujitsu-onecompression-arbitrary-code-execution-via-torch-load-deserialization third-party-advisory