Detections
Analytics

SCA: security update for vllm (GHSA-rh4j-5rhw-hr54)

high Tenable Cloud Security Plugin ID 420775

Description

There are packages installed that are affected by a vulnerability referenced in the following CVE:

 - 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.
 (CVE-2025-24357)

See Also

https://github.com/advisories/GHSA-rh4j-5rhw-hr54

Plugin Details

Severity: High

ID: 420775

Version: Revision 1.13

Type: Local

Family: SCA Checks

Published: 1/28/2025

Updated: 7/2/2026

Supported Sensors: Tenable Cloud Security, Tenable Self-Hosted Container Security

Risk Information

VPR

Risk Factor: Medium

Score: 6.9

Percentile: 97.07

Vendor

Vendor Severity: High

CVSS v2

Risk Factor: Critical

Base Score: 10

Temporal Score: 7.4

Vector: CVSS2#AV:N/AC:L/Au:N/C:C/I:C/A:C

CVSS Score Source: CVE-2025-24357

CVSS v3

Risk Factor: High

Base Score: 8.8

Temporal Score: 7.7

Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Temporal Vector: CVSS:3.0/E:U/RL:O/RC:C

Vulnerability Information

Exploit Ease: No known exploits are available

Patch Publication Date: 1/27/2025

Vulnerability Publication Date: 1/27/2025

Reference Information

CVE: CVE-2025-24357

cwe: CWE-502