---
id: CVE-2026-114053
title: vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision
summary: >-
  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…
severity: high
cvss: 8.1
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H'
cvssSource: cna
cwe:
  - CWE-94
vendor: vllm-project
product: vllm
affected:
  - vllm >= 0.7.3 < 0.31.0
published: '2026-10-21'
updated: '2026-10-21'
sourceUpdated: '2026-10-21T00:36:29.796Z'
source: CVEORG
sourceUrl: 'https://www.cve.org/CVERecord?id=CVE-2026-114053'
references:
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-6mm3-gc2m
    label: GitHub Security Advisory (GHSA-h3rc-6mm3-gc2m)
  - url: >-
      https://github.com/vllm-project/vllm/commit/570735520942b6428ae98f1eb442c6d88adae55e
    label: Patch Commit
  - url: >-
      https://www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-rce-via-mm-processor-kwargs-code-revision
    label: >-
      VulnCheck Advisory: vLLM 0.7.3 before 0.31.0 RCE via
      mm_processor_kwargs.code_revision
tags:
  - cve.org
ingestedAt: '2026-10-21T01:37:08.042Z'
---

## Overview

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

- `vllm >= 0.7.3 < 0.31.0`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.