NewApp Monitoring is liveSign up free
AgentbeamBeta
AI agent vulnerability · vLLM

GHSA-f623-hjm8-5wg5: Duplicate Advisory: vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution

criticalCVSS 4.0 9.2 · 3.1 8.1

This advisory was withdrawn on Oct 27, 2026. The publisher no longer considers it a valid vulnerability.

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-h3rc-6mm3-gc2m.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 mmprocessorkwargs.coderevision to Transformers AutoProcessor.frompretrained, letting clients select which revision of a model's dynamic processor code is imported when…

Published Oct 21, 2026 · Updated Oct 27, 2026

Affected packages

vllm

Ecosystem
PyPI
Affected
>= 0.7.3, < 0.31.0
Fixed in
0.31.0
Check
pip show vllm

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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This advisory has been withdrawn because it is a duplicate of GHSA-h3rc-6mm3-gc2m.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.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More vLLM vulnerabilities

All vLLM entries