6.5

CVE-2026-34755

vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.
Verknüpft mit AI von unstrukturierten Daten zu bestehenden CPE der NVD
Diese Information steht angemeldeten Benutzern zur Verfügung. Login Login
Daten sind bereitgestellt durch das CVE Programm von einer CVE Numbering Authority (CNA) (Unstrukturiert).
Herstellervllm-project
≫
Produkt vllm
Version >= 0.7.0, < 0.19.0
Status affected
Zu dieser CVE wurde keine CISA KEV oder CERT.AT-Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 0.04% 0.136
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
security-advisories@github.com 6.5 2.8 3.6
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CWE-770 Allocation of Resources Without Limits or Throttling

The product allocates a reusable resource or group of resources on behalf of an actor without imposing any restrictions on the size or number of resources that can be allocated, in violation of the intended security policy for that actor.