vllm-project vLLM up to 0.29.x Video Backend Qwen2VLVideoBackend/Qwen3VLVideoBackend allocation of resources

CVSS Meta Temp Score
CVSS is a standardized scoring system to determine possibilities of attacks. The Temp Score considers temporal factors like disclosure, exploit and countermeasures. The unique Meta Score calculates the average score of different sources to provide a normalized scoring system.
Current Exploit Price (≈)
Our analysts are monitoring exploit markets and are in contact with vulnerability brokers. The range indicates the observed or calculated exploit price to be seen on exploit markets. A good indicator to understand the monetary effort required for and the popularity of an attack.
CTI Interest Score
Our Cyber Threat Intelligence team is monitoring different web sites, mailing lists, exploit markets and social media networks. The CTI Interest Score identifies the interest of attackers and the security community for this specific vulnerability in real-time. A high score indicates an elevated risk to be targeted for this vulnerability.
5.2$0-$5k2.28

Summaryinfo

A vulnerability labeled as problematic has been found in vllm-project vLLM up to 0.29.x. This affects the function Qwen2VLVideoBackend/Qwen3VLVideoBackend of the component Video Backend. The manipulation of the argument media_io_kwargs.video.max_frames/media_io_kwargs.video.fps results in allocation of resources. This vulnerability is known as CVE-2026-105758. It is possible to launch the attack remotely. No exploit is available. The affected component should be upgraded.

Detailsinfo

A vulnerability, which was classified as problematic, was found in vllm-project vLLM up to 0.29.x. Affected is the function Qwen2VLVideoBackend/Qwen3VLVideoBackend of the component Video Backend. The manipulation of the argument media_io_kwargs.video.max_frames/media_io_kwargs.video.fps with an unknown input leads to a allocation of resources vulnerability. CWE is classifying the issue as CWE-770. The product allocates a reusable resource or group of resources on behalf of an actor without imposing any restrictions on the size or number of resources that can be allocated, in violation of the intended security policy for that actor. This is going to have an impact on availability. CVE summarizes:

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.

The advisory is available at github.com. This vulnerability is traded as CVE-2026-105758 since 10/05/2026. The exploitability is told to be easy. It is possible to launch the attack remotely. The exploitation doesn't require any form of authentication. Technical details are known, but there is no available exploit. This vulnerability is assigned to T1499 by the MITRE ATT&CK project.

Upgrading to version 0.30.0 eliminates this vulnerability.

The vulnerability is also documented in the vulnerability database at EUVD (EUVD-2026-92848). If you want to get best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Type

Vendor

Name

Version

Website

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔒
VulDB Reliability: 🔍

CVSSv3info

VulDB Meta Base Score: 5.3
VulDB Meta Temp Score: 5.2

VulDB Base Score: 5.3
VulDB Temp Score: 5.1
VulDB Vector: 🔒
VulDB Reliability: 🔍

CNA Base Score: 5.3
CNA Vector (GitHub_M): 🔒

CVSSv2info

AVACAuCIA
💳💳💳💳💳💳
💳💳💳💳💳💳
💳💳💳💳💳💳
VectorComplexityAuthenticationConfidentialityIntegrityAvailability
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock

VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍

Exploitinginfo

Class: Allocation of resources
CWE: CWE-770 / CWE-400 / CWE-404
CAPEC: 🔒
ATT&CK: 🔒

Physical: No
Local: No
Remote: Yes

Availability: 🔒
Status: Not defined
Price Prediction: 🔍
Current Price Estimation: 🔒

0-DayUnlockUnlockUnlockUnlock
TodayUnlockUnlockUnlockUnlock

Threat Intelligenceinfo

Interest: 🔍
Active Actors: 🔍
Active APT Groups: 🔍

Countermeasuresinfo

Recommended: Upgrade
Status: 🔍

0-Day Time: 🔒

Upgrade: vLLM 0.30.0

Timelineinfo

10/05/2026 CVE reserved
10/05/2026 +0 days VulDB entry created
10/06/2026 +0 days Advisory disclosed
10/06/2026 +0 days VulDB entry last update

Sourcesinfo

Product: github.com

Advisory: github.com
Status: Confirmed

CVE: CVE-2026-105758 (🔒)
GCVE (CVE): GCVE-0-2026-105758
GCVE (VulDB): GCVE-100-413850
EUVD: 🔒

Entryinfo

Created: 10/06/2026 01:09
Updated: 10/06/2026 02:55
Changes: 10/06/2026 01:09 (67), 10/06/2026 02:55 (1)
Complete: 🔍
Cache ID: 216::103

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion

No comments yet. Languages: en.

Please log in to comment.

Do you want to use VulDB in your project?

Use the official API to access entries easily!