Detections
Analytics

SCA: security update for vllm (GHSA-grg2-63fw-f2qr)

high Tenable Cloud Security Plugin ID 436716

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). In versions from 0.6.4 to before
 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model
 implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch
 that results in an unhandled runtime error, leading to complete server termination. This issue has been
 patched in version 0.12.0. (CVE-2026-22773)

See Also

https://github.com/advisories/GHSA-grg2-63fw-f2qr

Plugin Details

Severity: High

ID: 436716

Version: Revision 1.6

Type: Local

Family: SCA Checks

Published: 1/13/2026

Updated: 7/2/2026

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

Risk Information

VPR

Risk Factor: Low

Score: 3

Percentile: 23.73

Vendor

Vendor Severity: Medium

CVSS v2

Risk Factor: High

Base Score: 7.8

Temporal Score: 6.1

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

CVSS Score Source: CVE-2026-22773

CVSS v3

Risk Factor: High

Base Score: 7.5

Temporal Score: 6.7

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

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

Vulnerability Information

Exploit Available: true

Exploit Ease: Exploits are available

Patch Publication Date: 1/13/2026

Vulnerability Publication Date: 1/10/2026

Reference Information

CVE: CVE-2026-22773

cwe: CWE-770