CVEFinder.io

CVE-2026-105758

đŸ”ļ medium
🔍 Scan for this CVE
Summary

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 memor

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.

CVSS Score
5.3
Medium
EPSS Score
0.3
Exploit Probability
Published Date
2026-10-05
First Seen: 2026-10-08
📊 Relative Risk Intelligence

This CVE is Lower Risk - more severe than 19.0% of all 365,616 vulnerabilities in our database.

#296,291
Below average severity
Severity Percentile
Last Modified 2026-10-08
Source NVD 🔗
CVSS Vector 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
CWE IDs (Weakness Types)
CWE-770

đŸ“Ļ Affected Products 1

Vendor Product Status Affected Versions
vllm vllm Affected
> 0.24.0 < 0.30.0

🔗 References 4

https://github.com/vllm-project/vllm/commit/ea723c81...
Patch
https://github.com/vllm-project/vllm/pull/56729
Issue Tracking Patch
https://github.com/vllm-project/vllm/releases/tag/v0...
Release Notes
https://github.com/vllm-project/vllm/security/adviso...
Mitigation Vendor Advisory

🔗 Related CVEs 6

CVE ID Severity CVSS EPSS Summary Published
CVE-2026-105752 ℹī¸ low 3.1 0.2 vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted... 2026-10-05
CVE-2026-105753 đŸ”ļ medium 6.5 0.4 vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU ... 2026-10-05
CVE-2026-105754 đŸ”ļ medium 6.5 0.3 vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint ... 2026-10-05
CVE-2026-105755 đŸ”ļ medium 4.2 0.2 vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at th... 2026-10-05
CVE-2026-105756 đŸ”ļ medium 6.5 0.3 vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models acc... 2026-10-05
CVE-2026-105757 đŸ”ļ medium 6.5 0.3 vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures c... 2026-10-05
These CVEs affect the same products