HomeVllmCVE-2025-24357

CVE-2025-24357

HIGH
7.5CVSS
Published: 2025-01-27
Updated: 2025-06-27
AI Analysis

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.

CVSS Metrics

Vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack Vector
network
Complexity
high
Privileges
none
User Action
required
Scope
unchanged
Confidentiality
high
Integrity
high
Availability
high
Weaknesses
CWE-502

Metadata

Primary Vendor
VLLM
Published
1/27/2025
Last Modified
6/27/2025
Source
NIST NVD
Note: Verify all details with official vendor sources before applying patches.

Affected Products

vllm : vllm

AI-Powered Remediation

Generate remediation guidance or a C-suite brief for this vulnerability.

Executive Intelligence Brief

CVE-CVE-2025-24357 | HIGH Severity | CVEDatabase.com | CVEDatabase.com