vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach (vllm-project vllm)

CVE-2026-105758
MEDIUM 5.3

At a glance

Source
NVD
EPSS
EPSS 0.30 % · percentile 23 ()
State
PUBLISHED
Published
Updated
Assigner
GitHub_M
NVD status
Analyzed

Description

vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields without enforcing server-side ceilings. An unauthenticated caller can submit these values to the /tokenize endpoint, causing the sampler to decode every frame selected from attacker-controlled video input, consume disproportionate frontend memory, and potentially terminate the API process before scheduling or admission control. The Rust frontend is not affected because it rejects the media_io_kwargs field. This issue is fixed in version 0.30.0.

Weaknesses (CWE)

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

References

Scores

VersionScoreVectorScored by
CVSS 3.1MEDIUM 5.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:LGitHub_M
CVSS 3.1MEDIUM 5.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:LNVD · security-advisories@github.com (Secondary)

Advisories

European references

Affected configurations (NVD CPE)

Affected products

ProductVersions
vllm-project · vllmaffected >= 0.24.0, < 0.30.0

Sources

SourceLicence
CVE List (CVEProject cvelistV5)CVE Program Terms of Use
EPSS (FIRST.org)FIRST — attribution requested
ENISA EUVDENISA — reproduction authorised, source acknowledged
NVD (NIST) via fkie-cad/nvd-json-data-feedsPublic domain — this product uses data from the NVD API but is not endorsed or certified by the NVD