Detections
Analytics

SCA: security update for vllm (GHSA-pq5c-rjhq-qp7p)

medium Tenable Cloud Security Plugin ID 446166

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 0.7.0 to before 0.19.0, the
 VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma
 to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter
 (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg
 base64 path. An attacker can send a single API request containing thousands of comma-separated
 base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This
 vulnerability is fixed in 0.19.0. (CVE-2026-34755)

Solution

Update the vllm library and its related packages to version 0.19.0 or later.

See Also

https://github.com/advisories/GHSA-pq5c-rjhq-qp7p

Plugin Details

Severity: Medium

ID: 446166

Version: Revision 1.1

Type: Local

Family: SCA Checks

Published: 8/20/2026

Updated: 8/20/2026

Risk Information

VPR

Risk Factor: Low

Score: 3

Percentile: 23.72

Vendor

Vendor Severity: Medium

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-2026-34755

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

Vulnerability Information

Exploit Ease: No known exploits are available

Patch Publication Date: 4/3/2026

Vulnerability Publication Date: 4/3/2026

Reference Information

CVE: CVE-2026-34755

cwe: CWE-770