TI-2026-68371 Aliases CVE-2026-105760 GHSA-58v5-2m8f-94pr

vLLM GLMGA video sampling lets requests exhaust CPU and memory

LOW 30CWE-400Published 2026-10-05 · Updated 2026-10-06

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-400.

Summary

vLLM versions from 0.23.0rc2 before 0.30.0 are affected. The GLMGA video backend builds and deduplicates a frame-index list sized by request-level fps and max_frames values, with no strict work ceiling (CWE-400). A remote caller without privileges can send a compact request with a tiny valid video to consume excessive CPU and memory in the shared media-loading executor, which degrades availability.

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. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV

EPSS 0.00297 22nd 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	0.23.0rc2 to before 0.30.0	0.30.0	Patch available	CNA
—	vllm (PyPI)	0.23.0rc2 to before 0.30.0	0.30.0	Patch available	GHSA-58v5-2m8f-94pr

vllm Vendorvllm-project Affected 0.23.0rc2 to before 0.30.0 Fixed in 0.30.0 Patch available CNA
vllm (PyPI) Vendor— Affected 0.23.0rc2 to before 0.30.0 Fixed in 0.30.0 Patch available GHSA-58v5-2m8f-94pr

CPE configurations NVD · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:vllm:vllm::::::::	0.23.0 to before 0.30.0	Vulnerable	vLLM

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.23.0 to before 0.30.0 Vulnerable ·vLLM

Remediation

Upgrade vLLM to version 0.30.0, which fixes this issue. Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3 and Red Hat OpenShift AI (RHOAI) are affected, and Red Hat lists no available plan for them.

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-58v5-2m8f-94pr 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-2026-105760
2026-10-06 Alias added: GHSA-58v5-2m8f-94pr
2026-10-06 Fix available: PyPI/[email protected] · GHSA-58v5-2m8f-94pr
2026-10-06 CVSS score added · GHSA-58v5-2m8f-94pr
2026-10-06 Weakness changed · GHSA-58v5-2m8f-94pr
2026-10-06 5 new references · GHSA-58v5-2m8f-94pr
2026-10-06 Affected versions changed · Red Hat
2026-10-06 CVSS score added · Red Hat
2026-10-06 CISA SSVC decision points changed

References

Patch 2

Advisory 1

https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr

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