SEPTEMBER 19, 2026
Live Feed
Back to database
Case File

CVE-2026-73325

HIGH · CVSS 7.8 EPSS 0.26% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-08-12 · Last synced 2026-09-11

CyberRota Analysis

AI-Generated

The OneCompression library version 1.2.0 is vulnerable to an unsafe deserialization flaw that enables attackers to execute arbitrary code by providing a specially crafted model.pt checkpoint file. This vulnerability arises from the unguarded invocation of Python's pickle mechanism during the loading process, allowing malicious payloads to be executed. Organizations utilizing this library, particularly those in machine learning or data processing, should prioritize remediation to mitigate the risk of remote code execution.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

GitHub PoC Links

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-73325
Severity
HIGH
CVSS
7.8
EPSS
0.26%

Original NVD 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.