CVEvulnerability

CVE-2026-34755

6.5 MEDIUM Published 2026-04-06 Modified 2026-08-25 Official page ↗
Status
Modified
Published
2026-04-06
Last modified
2026-08-25
Assigner
[email protected]
CVSS 3.1 ([email protected])
6.5 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CVSS 3.1 (0b0ca135-0b70-47e7-9f44-1890c2a1c46c)
6.5 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Weaknesses
CWE-770

Description

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.

Affected configurations

• vllm vllm (>= 0.7.0 < 0.19.0)

Related

Weakness · CWE (1)

  • CWE-770 Allocation of Resources Without Limits or Throttling weakness

References