Bug 2431865 (CVE-2026-22807)

Summary:	CVE-2026-22807 vLLM: vLLM: Arbitrary code execution via untrusted model loading
Product:	[Other] Security Response	Reporter:	OSIDB Bzimport <bzimport>
Component:	vulnerability	Assignee:	Product Security DevOps Team <prodsec-dev>
Status:	NEW ---	QA Contact:
Severity:	high	Docs Contact:
Priority:	high
Version:	unspecified	CC:	alinfoot, bbrownin, dtrifiro, jkoehler, lphiri, rbryant, weaton
Target Milestone:	---	Keywords:	Security
Target Release:	---
Hardware:	All
OS:	Linux
Whiteboard:
Fixed In Version:		Doc Type:	---
Doc Text:	A flaw was found in vLLM, an inference and serving engine for large language models (LLMs). This vulnerability allows a remote attacker to achieve arbitrary code execution on the vLLM host during model loading. This occurs because vLLM loads Hugging Face `auto_map` dynamic modules without properly validating the `trust_remote_code` setting. By influencing the model repository or path, an attacker can execute malicious Python code at server startup, even before any API requests are handled.	Story Points:	---
Clone Of:		Environment:
Last Closed:		Type:	---
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2026-01-21 22:01:22 UTC

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.