---
id: CVE-2026-116172
title: >-
  vllm: vLLM: Denial of Service via improper input validation in Rust gRPC
  interface (CVE-2026-116172)
summary: >-
  A flaw was found in vLLM. Due to improper input validation in the Rust gRPC
  interface, a remote attacker can bypass configured limits by sending requests
  with excessively large or wrapped token count values. When processed, these
  invalid v…
severity: medium
cvss: 5.9
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H'
cvssSource: vendor
cwe:
  - CWE-1284
  - CWE-20
vendor: Red Hat
product: Red Hat AI Inference Server
affected:
  - ai_inference_server
  - enterprise_linux_ai_rhel_ai 3
  - openshift_ai_rhoai
published: '2026-10-25'
updated: '2026-10-25'
sourceUpdated: '2026-10-25T13:45:12+00:00'
source: CSAF
sourceUrl: 'https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-116172.json'
references:
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-116172.json
  - url: 'https://access.redhat.com/security/cve/CVE-2026-116172'
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2560388'
  - url: 'https://www.cve.org/CVERecord?id=CVE-2026-116172'
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-116172'
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-rwfw-xvg3-3937
  - url: >-
      https://www.vulncheck.com/advisories/vllm-0.22.0-before-0.24.0-dos-via-rust-grpc-candidatetokens-top-n
tags:
  - csaf
  - vex
  - red-hat
  - cve.org
ingestedAt: '2026-10-25T22:08:29.948Z'
epss: 0.00348
epssPercentile: 0.28184
---

## Overview

A flaw was found in vLLM. Due to improper input validation in the Rust gRPC interface, a remote attacker can bypass configured limits by sending requests with excessively large or wrapped token count values. When processed, these invalid values trigger internal sampling failures that terminate the core engine service, resulting in a Denial of Service (DoS).

## Vendor advisories

- **Red Hat VEX** · Moderate · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · no fix planned: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-10-25 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-116172.json)

**vllm: vLLM: Denial of Service via improper input validation in Rust gRPC interface** — rated Moderate by Red Hat. Released 2026-10-25.

Affected:

- Red Hat AI Inference Server
- Red Hat Enterprise Linux AI (RHEL AI) 3
- Red Hat OpenShift AI (RHOAI)

No fix planned:

- Red Hat AI Inference Server
- Red Hat Enterprise Linux AI (RHEL AI) 3
- Red Hat OpenShift AI (RHOAI)

## Remediation

Fix deferred