CVE-2026-116174

Description

A flaw was found in vLLM. A remote attacker can trigger a Denial of Service (DoS) by submitting requests containing out-of-bounds token identifiers to the gRPC service. Because the application fails to validate pre-tokenized input against the model vocabulary before processing, handling these invalid values causes the core engine to terminate unexpectedly and leaves the server unavailable.

Statement

Moderate impact is assigned to this vulnerability because exploitation leads solely to a denial of service through an engine crash, without compromising data confidentiality or system integrity. Within Red Hat OpenShift AI and Red Hat Enterprise Linux AI deployments, the vLLM gRPC interface is generally deployed within internal container networks and protected by ingress routing or authentication mechanisms. Additionally, container orchestration platforms limit prolonged availability impact by automatically restarting terminated worker pods.

Common Vulnerability Scoring System (CVSS) Score Details

Info alert:Important note

CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).

The following CVSS metrics and score provided are preliminary and subject to review.

CVSS v3 Score Breakdown

Red HatNVDcve.org
Base Score5.97.55.9
Attack VectorNetworkNetworkNetwork
Attack ComplexityHighLowHigh
Privileges RequiredNoneNoneNone
User InteractionNoneNoneNone
ScopeUnchangedUnchangedUnchanged
ConfidentialityNoneNoneNone
Integrity ImpactNoneNoneNone
Availability ImpactHighHighHigh

Vector

Red Hat: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H

NVD: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

cve.org: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H

Understanding the Weakness (CWE)

Other

Technical Impact: Varies by Context

Frequently Asked Questions

Want to get errata notifications? Sign up here.