---
id: CVE-2026-27893
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 0.18.0, two model
  implementation files hardcode `trust_remote_code=True` when loading
  sub-components, bypassing the…
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-693
  - CWE-501
vendor: vllm
product: vllm
affected:
  - 'vllm >= 0.10.1, < 0.18.0'
patched:
  - vllm 0.18.0
published: '2026-03-27'
updated: '2026-07-08'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-27893'
references:
  - url: >-
      https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/pull/36192'
    label: security-advisories@github.com
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
    label: security-advisories@github.com
  - url: 'https://access.redhat.com/errata/RHSA-2026:10140'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:10141'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:19712'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:19724'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:19725'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:24977'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:8746'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:8747'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:8748'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/security/cve/CVE-2026-27893'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2452055'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-27893'
  - url: 'https://github.com/vllm-project/vllm'
  - url: >-
      https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2297.yaml
  - url: 'https://access.redhat.com/errata/RHSA-2026:37275'
tags:
  - nvd
  - osv
  - pip
epss: 0.01346
epssPercentile: 0.7021
ingestedAt: '2026-07-08T13:51:10.434Z'
aliases:
  - GHSA-7972-pg2x-xr59
  - PYSEC-2026-2297
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 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.

## Affected

- `vllm >= 0.10.1, < 0.18.0`

## Remediation

Upgrade past the affected range:

- `vllm 0.18.0`

## Package advisory (CVE-2026-27893)

Affected packages:

- `vllm >= 0.10.1, < 0.18.0`

Patched in:

- `vllm 0.18.0`

Source: https://osv.dev/vulnerability/GHSA-7972-pg2x-xr59