Detections
Analytics

SCA: security update for vllm (GHSA-pmqf-x6x8-p7qw)

high Tenable Self-Hosted Container Security Plugin ID 436129

Description

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

 - vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before
 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs
 with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is
 intended to support such inputs (as defined in the Supported Models page). This issue has been patched in
 version 0.11.1. (CVE-2025-62372)

See Also

https://github.com/advisories/GHSA-pmqf-x6x8-p7qw

Plugin Details

Severity: High

ID: 436129

Version: Revision 1.7

Type: Local

Family: SCA Checks

Published: 11/21/2025

Updated: 7/2/2026

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

Risk Information

VPR

Risk Factor: Low

Score: 3

Percentile: 23.69

Vendor

Vendor Severity: High

CVSS v2

Risk Factor: Medium

Base Score: 6.8

Temporal Score: 5

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

CVSS Score Source: CVE-2025-62372

CVSS v3

Risk Factor: Medium

Base Score: 6.5

Temporal Score: 5.7

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

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

CVSS v4

Risk Factor: High

Base Score: 8.3

Threat Score: 5.7

Threat Vector: CVSS:4.0/E:U

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H

Vulnerability Information

Exploit Ease: No known exploits are available

Patch Publication Date: 11/20/2025

Vulnerability Publication Date: 11/20/2025

Reference Information

CVE: CVE-2025-62372

cwe: CWE-129