CVE-2026-73325
Published:August 12, 2026
Updated:August 31, 2026
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.
Affected Packages
onecomp (PYTHON):
Affected version(s) >=1.0.0 <1.2.1Fix Suggestion:
Update to version 1.2.1Additional Notes
The description of this vulnerability differs from MITRE.
Related Resources (6)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.4
Attack Vector
LOCAL
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
ACTIVE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
HIGH
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
7.8
Attack Vector
LOCAL
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
REQUIRED
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH
Weakness Type (CWE)
Deserialization of Untrusted Data
EPSS
Base Score:
0.26