CVE-2026-5497

published 11 Jun 2026 · updated 22 Jul 2026

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

7.5HighCVSS 7.5EPSS 1%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 1%. Fixed in 0.19.0.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
vllm-project<0.19.00.19.0

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-5497 severity on Zeptric[![CVE-2026-5497](https://zeptric.io/badge/cve/CVE-2026-5497.svg)](https://zeptric.io/cve/CVE-2026-5497)