Record summary

CVE-2026-73325 has a selected CVSS score of 8.4 (high).

Description

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.

Description source: CVE List

Exploitation context

CISA SSVC decision

ExploitationNone
AutomatableNo
Technical impactTotal

CISA Coordinator · SSVC 2.0.3 · Evaluated Aug 12, 2026 · Source: CVE List

Affected products and versions

1
ProductSourceVersion rangeStatus

Default status: affected

CVE ListThrough 1.2.0affected

Research & analysis

1
Advisory analysisNir Yehoshua, Cipher Security Labs / VulnCheckSource: EIP research review

Fujitsu OneCompression 1.2.0 Arbitrary Code Execution via torch.load Deserialization

VulnCheck advisory for CVE-2026-73325 (CVSS 8.4, CWE-502) in Fujitsu Research's OneCompression library version 1.2.0. The QuantizedModelLoader.load_quantized_model_pt() function unconditionally calls torch.load with weights_only=False, invoking Python's pickle deserialization on model checkpoint files. Attackers can embed malicious __reduce__ methods in a crafted model.pt checkpoint to execute arbitrary Python code, including system commands, when the library loads the file from a caller-selected model directory. Fixed in version 1.2.1 with an opt-in allow_unsafe_deserialization=True parameter; safetensors-based loading is recommended for untrusted models. Discovered by Nir Yehoshua from Cipher Security Labs and independently corroborated by the vendor's CHANGELOG.md.

Root causeTechnical detailMitigation
https://www.vulncheck.com/advisories/fujitsu-onecompression-arbitrary-code-execution-via-torch-load-deserialization
Research notes
Supporting sources

References

3