PatchRadar

← Browse

CVE-2026-22807

Medium

Elevated severity or exploit probability.

CVSS base
8.8 HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS — probability of exploitation (30 days)
0.8%
55.8th percentile
CISA KEV
Not listed
Weakness / dates
CWE-94
Published 2026-01-21 · modified 2026-07-21

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

vllm

References

Official: NVD · CVE.org