cbcvebase.
CVE-2026-34755
published 2026-04-06

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…

PriorityP337medium6.5CVSS 3.1
AVNACLPRLUINSUCNINAH
EPSS
0.35%
26.9th percentile
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

3 ranges
VendorProductVersion rangeFixed in
vllm-projectvllm
vllmvllm>= 0.7.0 < 0.19.00.19.0
vllmvllm>= 0.7.0 < 0.19.00.19.0

CVSS provenance

nvdv3.16.5MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
vendor_redhat6.5MEDIUM
Stop checking back — get the weekly exploitation signal.

Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.