CVE-2026-73325

Fujitsu OneCompression < 1.2.1 Arbitrary Code Execution via torch.load Deserialization

State
Published
Severity
8.4 High
Published
Aug 12, 2026
Updated
Aug 25, 2026
Reserved
Aug 11, 2026

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
4.08.4 HighCVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NVulnCheck
3.17.8 HighCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HVulnCheck

Weaknesses

  • CWE-502 Deserialization of Untrusted Data

Affected Products

ProductVersions
OneCompressionFujitsu Research
  • before 1.2.1Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.