Vulnerability 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.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/FujitsuResearch/OneCompression/blob/main/SECURITY.md
- https://pypi.org/project/onecomp/
- https://pypi.org/project/onecomp/1.2.1/
- https://www.vulncheck.com/advisories/fujitsu-onecompression-arbitrary-code-execu
FAQ
What is CVE-2026-73325?
CVE-2026-73325 is a vulnerability with a CVSS score of 7.8 (HIGH). 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,...
How severe is CVE-2026-73325?
CVE-2026-73325 has been rated HIGH with a CVSS base score of 7.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-73325?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.