CVE Database · CVE-2026-22807
CVSS v3.1
8.8
EPSS
0.73%
Published
Jan 21, 2026
Modified
Jan 30, 2026
Public PoC / Exploit
All weaponized →No public PoC or exploit code indexed for this CVE.
Links to public security research (Exploit-DB, Nuclei, Trickest, GitHub) for defensive use only.
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.
CVSS Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HWeaknesses (CWE)
Affected Products (1)
References (4)