---
id: GHSA-f623-hjm8-5wg5
title: >-
  Duplicate Advisory: vLLM: Request-controlled mm_processor_kwargs.code_revision
  allows remote code execution
summary: >-
  Duplicate Advisory: vLLM: Request-controlled mm_processor_kwargs.code_revision
  allows remote code execution
severity: critical
cvss: 8.1
cwe:
  - CWE-94
vendor: vllm
product: vllm
ecosystem: pip
affected:
  - 'vllm >= 0.7.3, < 0.31.0'
patched:
  - vllm 0.31.0
published: '2026-10-21'
updated: '2026-10-27'
sourceUpdated: '2026-10-27T15:36:11Z'
source: GHSA
sourceUrl: 'https://github.com/advisories/GHSA-f623-hjm8-5wg5'
references:
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-6mm3-gc2m
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-114053'
  - url: >-
      https://github.com/vllm-project/vllm/commit/570735520942b6428ae98f1eb442c6d88adae55e
  - url: >-
      https://www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-rce-via-mm-processor-kwargs-code-revision
  - url: 'https://github.com/advisories/GHSA-f623-hjm8-5wg5'
tags:
  - ghsa
  - pip
ingestedAt: '2026-10-27T16:11:58.709Z'
---

## Overview

## Duplicate Advisory

This advisory has been withdrawn because it is a duplicate of GHSA-h3rc-6mm3-gc2m. This link is maintained to preserve external references.

## Original Description
vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients select which revision of a model's dynamic processor code is imported when trust_remote_code is enabled. An attacker controlling a revision in the served model repository can send a multimodal request to the unauthenticated /tokenize endpoint to execute arbitrary Python in the vLLM API process.

## Affected packages

- `vllm >= 0.7.3, < 0.31.0`

## Remediation

Upgrade to a patched release:

- `vllm 0.31.0`