9.8

CVE-2026-22807

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.
Verknüpft mit AI von unstrukturierten Daten zu bestehenden CPE der NVD
Diese Information steht angemeldeten Benutzern zur Verfügung. Login Login
Daten sind bereitgestellt durch National Vulnerability Database (NVD)
Vllm ≫ Vllm Version >= 0.10.1 < 0.14.0
Zu dieser CVE wurde keine CISA KEV oder CERT.AT-Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 0.06% 0.175
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
nvd@nist.gov 9.8 3.9 5.9
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
security-advisories@github.com 8.8 2.8 5.9
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CWE-94 Improper Control of Generation of Code ('Code Injection')

The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.