CVE-2026-22807vLLM is an inference and serving engine for large language models (LLMs).

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.

CVSS

9.8 CRITICAL (v3.1, NVD)CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Weakness (CWE)

CWE-94

Known exploited

Not in CISA's KEV catalog

EPSS (exploitation in the next 30 days)

Not loaded for this CVE

Assigned by

Not given

NVD analysis

Modified

Record last updated

Jul 21, 2026

First seen by InfoSec Signals

Oct 9, 2026

The CVE record on cve.org · NVD's entry

The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.