CVE Database
/

CVE-2026-34755

Back to search

CVE-2026-34755

Published: Apr 6, 2026

Modified: Apr 6, 2026

PUBLISHED

CVSS v3.1

6.5

MEDIUM

Description

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.

VendorProductVersions

vllm-project

vllm

affected
>= 0.7.0, < 0.19.0

Weaknesses (CWE)

CVSS v3.1 Details

CVSS v3.1 Vector

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Unchanged

Confidentiality

None

Integrity

None

Availability

High

Security Training

Train your team to recognize and prevent security threats with our comprehensive security awareness program.

Start Training

Vulnerability Scanning

Discover vulnerabilities in your applications and infrastructure before attackers do.

Scan Now