Advisory

PYSEC-2026-144

Also known as: CVE-2026-34755, GHSA-pq5c-rjhq-qp7p

Summary

The record has no summary.

Details

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.

Severity

Medium Basis: CVSS v3 score 6.5, vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Dates

Published
2026-04-06 16:16 UTC
Modified
2026-05-20 09:19 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.7.0, fixed 0.19.0 (ecosystem)

Fixed versions

0.19.0

Fix

  • Fixed version 0.19.0
    pip install --upgrade vllm==0.19.0

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences