CVE-2025-24357

Published Jan 27, 2025

Last updated a month ago

Overview

Description
vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.
Source
security-advisories@github.com
NVD status
Received

Risk scores

CVSS 3.1

Type
Secondary
Base score
7.5
Impact score
5.9
Exploitability score
1.6
Vector string
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Severity
HIGH

Weaknesses

security-advisories@github.com
CWE-502

Social media

Hype score
Not currently trending