CVE-2025-24357

Severity CVSS v4.0:

Pending analysis

Type:

CWE-502 Deserialization of Untrusted Dat

Publication date:

27/01/2025

Last modified:

27/06/2025

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.

Impact

Vector 3.x

CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H CVSS v3.1 Severity and Metrics:

Base Score: 7.50 HIGH
Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H

Attack Vector (AV): Network
Attack Complexity (AC): High
Privileges Required (PR): None
User Interaction (UI): Required
Scope (S): Unchanged
Confidentiality (C): High
Integrity (I): High
Availability (A): High