7.5Alta

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

vllm-project vllm-project/vllm; Red Hat Red Hat AI Inference Server; Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3; Red Hat Red Hat OpenShift AI (RHOAI) Publicada: (hace 5 meses)

Descripción

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.

Debilidad (CWE): CWE-400CWE-770

Datos: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Se publican tal como los indican las fuentes, en inglés.

Productos y versiones afectados

FabricanteProductoVersiones
Red Hat Red Hat AI Inference Server all versions
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 all versions
Red Hat Red Hat OpenShift AI (RHOAI) all versions
vllm vllm 0.8.0 – < 0.19.0
vllm-project vllm-project/vllm unspecified – < 0.19.0

Referencias y parches

Coincidencias CPE (NVD) (1)

  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.8.0 < 0.19.0