CVE-2026-5497 HIGH

CVE-2026-5497: Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

Vendor Vllm-Project
Product vllm-project/vllm
Weakness CWE-400
Published June 11, 2026
Last update June 30, 2026

CVSS base score

7.5/10
Attack vector Network
Attack complexity Low
Privileges required None
User interaction None
Confidentiality None
Integrity None

CVSS vector

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

What the vulnerability does

01Description

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.

Key dates

02Disclosure timeline

June 11, 2026 CVE published
June 30, 2026 Record updated