| ID |
CVE-2026-105758
|
| Sažetak |
vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing server-side ceilings. An unauthenticated caller can submit these values to the /tokenize endpoint, causing the sampler to decode every frame selected from attacker-controlled video input, consume disproportionate frontend memory, and potentially terminate the API process before scheduling or admission control. The Rust frontend is not affected because it rejects the media_io_kwargs field. This issue is fixed in version 0.30.0. |
| Reference |
|
| CVSS |
| Base: | 5.3 |
| Impact: | 1.4 |
| Exploitability: | 3.9 |
|
| Pristup |
| Vektor | Složenost | Autentikacija |
| NETWORK |
LOW |
NONE |
|
| Impact |
| Povjerljivost | Cjelovitost | Dostupnost |
| NONE |
NONE |
LOW |
|
| CVSS vektor |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L |
| Zadnje važnije ažuriranje |
05-10-2026 - 23:17 |
| Objavljeno |
05-10-2026 - 23:17 |
