---
id: CVE-2026-22807
title: vLLM is an inference and serving engine for large language models (LLMs)
summary: >-
  vLLM is an inference and serving engine for large language models (LLMs).
  Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging
  Face `auto_map` dynamic modules during model resolution without gating on
  `trust_remote_…
severity: high
cvss: 8.8
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'
cwe:
  - CWE-94
vendor: vllm
product: vllm
affected:
  - 'vllm >= 0.10.1, < 0.14.0'
patched:
  - vllm 0.14.0
published: '2026-01-21'
updated: '2026-06-30'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-22807'
references:
  - url: >-
      https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/pull/32194'
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/releases/tag/v0.14.0'
    label: security-advisories@github.com
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr
    label: security-advisories@github.com
  - url: 'https://access.redhat.com/errata/RHSA-2026:10184'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:30087'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:30088'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:30089'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:3461'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:3462'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:3713'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:3782'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:5119'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/security/cve/CVE-2026-22807'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2431865'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-22807.json
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-22807'
  - url: 'https://pypi.org/project/vllm'
  - url: 'https://github.com/vllm-project/vllm'
  - url: >-
      https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2010.yaml
  - url: 'https://github.com/advisories/GHSA-2pc9-4j83-qjmr'
  - url: 'https://access.redhat.com/errata/RHSA-2026:42644'
tags:
  - nvd
  - exploit-available
  - osv
  - pip
epss: 0.0083
epssPercentile: 0.55698
ingestedAt: '2026-06-30T13:26:50.533Z'
exploits:
  github: 1
  githubRepos:
    - 'https://github.com/otakuliu/CVE-2026-22807_Range'
  checkedAt: '2026-09-25T08:20:52.998Z'
exploitAvailable: true
aliases:
  - GHSA-2pc9-4j83-qjmr
  - PYSEC-2026-2010
ecosystem: pip
---

## Overview

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.

## Affected

- `vllm >= 0.10.1, < 0.14.0`

## Remediation

Upgrade past the affected range:

- `vllm 0.14.0`

## Package advisory (CVE-2026-22807)

Affected packages:

- `vllm >= 0.10.1, < 0.14.0`

Patched in:

- `vllm 0.14.0`

Source: https://osv.dev/vulnerability/GHSA-2pc9-4j83-qjmr