TI-2026-68369 Aliases CVE-2026-105758 GHSA-x6mc-67gf-chw4

Unbounded video frame sampling in vLLM Qwen2-VL and Qwen3-VL backends

LOW 30CWE-770Published 2026-10-05 · Updated 2026-10-08

Key facts

Attack vector: Network
Privileges required: None
User interaction: None
Attack complexity: Low
Impact type: Denial of service
Confidentiality · integrity · availability: None · None · Low
Fix status: Partial Red Hat: 3 without a fix

Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-770.

Summary

vLLM from 0.24.0 before 0.30.0 accepts request-level max_frames and fps video settings in its Qwen2-VL and Qwen3-VL video backends without server-side ceilings (CWE-770). An unauthenticated remote attacker can send such values to the /tokenize endpoint, forcing the sampler to decode many frames from attacker-supplied video. This consumes excessive frontend memory and can terminate the API process.

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

Description from the CNA

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV

EPSS 0.00303 23rd percentileScored 2026-11-07

Fix Partial vllm (vllm-project): 0.30.0vllm (PyPI): 0.30.0Red Hat: 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation: None
Automatable: Yes
Technical impact: Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

Vendor	Product	Affected versions	Fixed in	Status	Source
vllm-project	vllm	0.24.0 to before 0.30.0	0.30.0	Patch available	CNA
—	vllm (PyPI)	0.24.0 to before 0.30.0	0.30.0	Patch available	GHSA-x6mc-67gf-chw4

vllm Vendorvllm-project Affected 0.24.0 to before 0.30.0 Fixed in 0.30.0 Patch available CNA
vllm (PyPI) Vendor— Affected 0.24.0 to before 0.30.0 Fixed in 0.30.0 Patch available GHSA-x6mc-67gf-chw4

CPE configurations NVD · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:vllm:vllm::::::::	0.24.0 to before 0.30.0	Vulnerable	vLLM

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.24.0 to before 0.30.0 Vulnerable ·vLLM

Remediation

Upgrade the PyPI vllm package to version 0.30.0. No fixed version is listed for Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, or Red Hat OpenShift AI (RHOAI).

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

Fix · CNA vllm (vllm-project) Fixed in 0.30.0
Fix · GHSA-x6mc-67gf-chw4 vllm (PyPI) Fixed in 0.30.0 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

Product	Status	Plan or fix
Red Hat AI Inference Server	Affected	No fix yet: Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3	Affected	No fix yet: Fix deferred
Red Hat OpenShift AI (RHOAI)	Affected	No fix yet: Fix deferred

Timeline

2026-10-06 Threatist record created from CVE-2026-105758
2026-10-06 Alias added: GHSA-x6mc-67gf-chw4
2026-10-06 Fix available: PyPI/[email protected] · GHSA-x6mc-67gf-chw4
2026-10-06 CVSS score added · GHSA-x6mc-67gf-chw4
2026-10-06 Weakness changed · GHSA-x6mc-67gf-chw4
2026-10-06 5 new references · GHSA-x6mc-67gf-chw4
2026-10-06 Affected versions changed · Red Hat
2026-10-06 CVSS score added · Red Hat
2026-10-08 CISA SSVC decision points changed

References

Patch 2

Advisory 1

https://github.com/vllm-project/vllm/security/advisories/GHSA-x6mc-67gf-chw4

Other 2

TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5

See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences