p PatchFirst

CVE-2026-5497

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

Esta página presenta datos de fuentes públicas de vulnerabilidades. Consulta el aviso original antes de actualizar.

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.

CVSS 7.5 · Alta · EPSS 0,5% · Corrección disponible

Publicación
Actualización

Pila tecnológica: python

Productos y versiones afectados

  • vllm-project/vllm

    Versiones
    • ≥ unspecified, < 0.19.0: Afectada (custom)

    Actualiza a 0.19.0

  • vllm PyPI

    Versiones
    • 0.10.0
    • 0.10.1
    • 0.10.1.1
    • 0.10.2
    • 0.11.0
    • 0.11.1
    • 0.11.2
    • 0.12.0
    • 0.13.0
    • 0.14.0
    • 0.14.1
    • 0.15.0
    • 0.15.1
    • 0.16.0
    • 0.17.0
    • 0.17.1
    • 0.18.0
    • 0.18.1
    • 0.8.0
    • 0.8.1
    • 0.8.2
    • 0.8.3
    • 0.8.4
    • 0.8.5
    • 0.8.5.post1
    • 0.9.0
    • 0.9.0.1
    • 0.9.1
    • 0.9.2
    Intervalos de versiones afectados
    • ECOSYSTEM: ≥ 0.8.0, < 0.19.0

    Actualiza a 0.19.0

Fuentes originales

Comprueba tu servidor →