CVE-2026-73325

HIGH 7.8

Fujitsu OneCompression 1.2.0 Arbitrary Code Execution via torch.load Deserialization

CVSS Score

7.8

EPSS Score

0.0%

EPSS Percentile

0th

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.

CWE	CWE-502
Vendor	fujitsu research
Product	onecompression
Published	Aug 12, 2026

Stay Ahead of the Next One

Get instant alerts for fujitsu research onecompression

Be the first to know when new high vulnerabilities affecting fujitsu research onecompression are published — delivered to Slack, Telegram or Discord.

Get Free Alerts → Free · No credit card · 60 sec setup

CVSS v3 Breakdown

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Attack Vector

Local

Attack Complexity

Low

Privileges Required

None

User Interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Affected Versions

Fujitsu Research / OneCompression

0 ≤ 1.2.0

References

NVD ↗ CVE.org ↗ EPSS Data ↗

pypi.org: https://pypi.org/project/onecomp/ pypi.org: https://pypi.org/project/onecomp/1.2.1/ vulncheck.com: https://www.vulncheck.com/advisories/fujitsu-onecompression-arbitrary-code-execution-via-torch-load-deserialization

Credits

Nir Yehoshua from Cipher Security Labs