vLLM request-controlled mm_processor_kwargs.code_revision remote code execution

Severity: high · CVSS 8.1 · Published 2026-10-21

vLLM is a language model serving platform that processes multimodal requests from clients. An attacker can send a specially crafted request to the unauthenticated /tokenize endpoint that causes vLLM to execute arbitrary Python code when the model uses dynamic processor code and trust_remote_code is enabled, potentially compromising the entire API process and any models or data it has access to.

Technologies: vllm (PyPI). Vendors: PyPI.

Quick answers

Is This vulnerability exploited in the wild?
No. Junglewise Threat Intelligence has no report of This vulnerability being exploited in the wild.
How severe is This vulnerability?
High severity, with a CVSS score of 8.1, published 21 October 2026.
Which products and versions are affected?
vllm (PyPI) >= 0.7.3, < 0.31.0, ECOSYSTEM:introduced=0.7.3,fixed=0.31.0.
Is there a fix for This vulnerability?
Yes. vllm (PyPI): upgrade to 0.31.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
Am I affected?
Check whether you run vllm (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

  • vllm (PyPI): upgrade to 0.31.0 or later
    pip install "vllm>=0.31.0"

Affected products

  • vllm (PyPI) >= 0.7.3, < 0.31.0, ECOSYSTEM:introduced=0.7.3,fixed=0.31.0

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.