TROYANOSYVIRUS
Back to CVEs

CVE-2026-22807

HIGH
8.8

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.

CVE Details

CVSS v3.1 Score8.8
SeverityHIGH
CVSS VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack VectorNETWORK
ComplexityLOW
Privileges RequiredNONE
User InteractionREQUIRED
Published1/21/2026
Last Modified1/30/2026
Sourcenvd
Honeypot Sightings0

Affected Products

vllm:vllm

Weaknesses (CWE)

CWE-94

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.