vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.

Project Subscriptions

Vendors Products
Vllm-project Subscribe
Advisories
Source ID Title
Github GHSA Github GHSA GHSA-ph72-cqr5-qpp7 vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features
Fixes

Solution

No solution given by the vendor.


Workaround

No workaround given by the vendor.

History

Tue, 06 Oct 2026 00:45:00 +0000

Type Values Removed Values Added
First Time appeared Vllm-project
Vllm-project vllm
Vendors & Products Vllm-project
Vllm-project vllm

Mon, 05 Oct 2026 23:00:00 +0000

Type Values Removed Values Added
Description vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.
Title vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features
Weaknesses CWE-1284
CWE-20
CWE-617
CWE-639
CWE-668
CWE-704
References
Metrics cvssV3_1

{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}


Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-10-05T22:46:03.163Z

Reserved: 2026-10-05T19:11:07.947Z

Link: CVE-2026-105754

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-10-05T23:17:02.017

Modified: 2026-10-05T23:17:02.017

Link: CVE-2026-105754

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-10-06T00:30:18Z