CVE-2026-34755
vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing
描述
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.
如何修補 CVE-2026-34755
要修補 CVE-2026-34755,請將受影響套件升級到下列已修補版本。
- —升級至 0.19.0 或更新版本
CVE-2026-34755 正在被利用嗎?
低 — EPSS 為 0.4%,目前沒有觀察到大規模利用活動。
受影響套件(1)
- >= 0.7.0, < 0.19.0
CVSS 分數
| 來源 | 版本 | 嚴重程度 | 向量 |
|---|---|---|---|
| osv | CVSS 3.1 | MEDIUM6.5 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |