PT-2026-48638 · Vllm · Vllm-Project/Vllm

Published 2026-06-11 · Updated 2026-06-11 · CVE-2026-5497

Mitre

CVSS v3.1

7.5

High

Base vector

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

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.

Fix

Resource Exhaustion

Weakness Enumeration

CWE-400

Related Identifiers

CVE-2026-5497

Affected Products

Vllm-Project/Vllm

References · 3

• https://nvd.nist.gov/vuln/detail/CVE-2026-5497 · Security Note
• https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395 · Note
• https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4 · Note