SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityModified

CVE-2026-34755

The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path.

MEDIUM 6.5EPSS 0.46%

Does this matter?

Lower severity and a low EPSS score (0.46%). Track it; it rarely justifies an emergency change on its own.

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.

CVSS 3.1
6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EPSS
0.46% probability · 39th percentile
CISA KEV
Not listed
Weakness
CWE-770
Affected
vllm/vllm
Source
security-advisories@github.com

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.