7.5

CVE-2026-5497

Exploit

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

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.
Daten sind bereitgestellt durch National Vulnerability Database (NVD)
Vllm ≫ Vllm Version >= 0.8.0 < 0.19.0
VulnDex Vulnerability Enrichment
Diese Information steht angemeldeten Benutzern zur Verfügung. Login Login
Zu dieser CVE wurde keine Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 0.42% 0.338
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
security@huntr.dev 7.5 3.9 3.6
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CWE-400 Uncontrolled Resource Consumption

The product does not properly control the allocation and maintenance of a limited resource, thereby enabling an actor to influence the amount of resources consumed, eventually leading to the exhaustion of available resources.

https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
Third Party Advisory
Exploit
https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
Patch