CVE-2026-73325
Fujitsu OneCompression < 1.2.1 Arbitrary Code Execution via torch.load Deserialization
CVSS Score
7.8
EPSS Score
0.3%
EPSS Percentile
17th
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.
| CWE | CWE-502 |
| Vendor | fujitsu research |
| Product | onecompression |
| Published | Aug 12, 2026 |
| Last Updated | Aug 25, 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 < 1.2.1
References
github.com: https://github.com/FujitsuResearch/OneCompression/blob/main/SECURITY.md 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