Skip to content
CVE PROGRAM SOURCE RECORD8.8 High

CVE-2026-22807

vLLM affected by RCE via auto_map dynamic module loading during model initialization

Read JSON ↗CVE.org ↗
Status
Published
Published
Updated
Assigning organization
GitHub_M

Description

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.

Affected products

Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.

vllm-project vllm

  • >= 0.10.1, < 0.14.0affected

References