--- id: CVE-2026-73325 title: >- 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_quantiz… summary: >- 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_quantiz… severity: high cvss: 7.8 cvssVector: 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H' cwe: - CWE-502 published: '2026-08-12' updated: '2026-09-24' sourceUpdated: '2026-09-24T20:43:32.537' source: NVD sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-73325' references: - url: 'https://github.com/FujitsuResearch/OneCompression/blob/main/SECURITY.md' label: disclosure@vulncheck.com - url: 'https://pypi.org/project/onecomp/' label: disclosure@vulncheck.com - url: 'https://pypi.org/project/onecomp/1.2.1/' label: disclosure@vulncheck.com - url: >- https://www.vulncheck.com/advisories/fujitsu-onecompression-arbitrary-code-execution-via-torch-load-deserialization label: disclosure@vulncheck.com tags: - nvd epss: 0.004 epssPercentile: 0.31494 ingestedAt: '2026-09-24T20:51:40.199Z' --- ## Overview 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. ## Remediation Refer to the linked advisories for vendor-supplied fixes and affected version ranges.