---
id: CVE-2026-105759
title: vLLM is an inference and serving engine for large language models
summary: >-
  vLLM is an inference and serving engine for large language models. Prior to
  0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP
  method token as a Prometheus label for requests reaching registered routes. An
  una…
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'
cwe:
  - CWE-400
  - CWE-770
vendor: vllm
product: vllm
affected:
  - vllm < 0.30.0
patched:
  - vllm 0.30.0
published: '2026-10-05'
updated: '2026-10-16'
sourceUpdated: '2026-10-16T20:41:27.840'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-105759'
references:
  - url: >-
      https://github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/pull/56058'
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/releases/tag/v0.30.0'
    label: security-advisories@github.com
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48
    label: security-advisories@github.com
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-105759.json
  - url: 'https://access.redhat.com/security/cve/CVE-2026-105759'
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2546208'
  - url: 'https://www.cve.org/CVERecord?id=CVE-2026-105759'
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-105759'
tags:
  - nvd
  - cve.org
  - exploit-available
  - csaf
  - vex
  - red-hat
  - osv
  - pip
epss: 0.00411
epssPercentile: 0.3519
aliases:
  - PYSEC-2026-4325
  - GHSA-5fj9-pfhr-6j48
ecosystem: pip
exploitAvailable: true
ssvc:
  exploitation: poc
  automatable: 'no'
  technicalImpact: partial
  timestamp: '2026-10-06T17:56:34.732350Z'
scores:
  nvd: 5.9
  osv: 7.5
ingestedAt: '2026-10-05T23:36:21.158Z'
---

## Overview

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.

## Affected

- `vllm < 0.30.0`

## Remediation

Upgrade past the affected range:

- `vllm 0.30.0`

## Package advisory (CVE-2026-105759)

Affected packages:

- `vllm < 0.30.0`

Patched in:

- `vllm 0.30.0`

Source: https://osv.dev/vulnerability/PYSEC-2026-4325

## 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 2026-10-16 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-105759.json)