8.8
/ 10
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
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.
Basic Information
ID
CVE-2026-22807
Source
GitHub_M
Published
Jan 21, 2026 at 21:13
Modified
Jan 22, 2026 at 16:50
Affected Product
Vendor
vllm-project
Product
vllm
Version
>= 0.10.1, < 0.14.0
Affected Versions
vllm-project vllm >= 0.10.1, < 0.14.0