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.
Published: 2026-10-21
Score: 9.2 Critical
EPSS: < 1% Very Low
KEV: No
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No solution or workaround provided in the CVE record.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-h3rc-6mm3-gc2m vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution
History

Thu, 29 Oct 2026 12:15:00 +0000

Type Values Removed Values Added
Weaknesses CWE-829
References
Metrics threat_severity

None

threat_severity

Important


Tue, 27 Oct 2026 23:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}


Thu, 22 Oct 2026 12:30:00 +0000

Type Values Removed Values Added
First Time appeared Vllm-project
Vllm-project vllm
Vendors & Products Vllm-project
Vllm-project vllm

Wed, 21 Oct 2026 00:45:00 +0000

Type Values Removed Values Added
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.
Title vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision
First Time appeared Vllm
Vllm vllm
Weaknesses CWE-94
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Vendors & Products Vllm
Vllm vllm
References
Metrics cvssV3_1

{'score': 8.1, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H'}

cvssV4_0

{'score': 9.2, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N'}


cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published:

Updated: 2026-10-27T21:41:51.602Z

Reserved: 2026-10-20T21:42:27.669Z

Link: CVE-2026-114053

cve-icon Vulnrichment

Updated: 2026-10-27T21:41:47.378Z

cve-icon NVD

Status : Undergoing Analysis

Published: 2026-10-21T01:17:28.083

Modified: 2026-10-27T22:17:23.940

Link: CVE-2026-114053

cve-icon Redhat

Severity : Important

Publid Date: 2026-10-21T00:36:29Z

Links: CVE-2026-114053 - Bugzilla

cve-icon OpenCVE Enrichment

Updated: 2026-10-29T13:30:08Z

Weaknesses
  • CWE-829

    Inclusion of Functionality from Untrusted Control Sphere

  • CWE-94

    Improper Control of Generation of Code ('Code Injection')