Description
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.
Published: 2025-12-01
Score: 7.1 High
EPSS: < 1% Very Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No vendor fix or workaround currently provided.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-8fr4-5q9j-m8gm vLLM vulnerable to remote code execution via transformers_utils/get_config
History

Fri, 05 Dec 2025 00:15:00 +0000

Type Values Removed Values Added
References
Metrics threat_severity

None

 threat_severity

Important

Wed, 03 Dec 2025 18:00:00 +0000

Type Values Removed Values Added
First Time appeared Vllm
Vllm vllm
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Vendors & Products Vllm
Vllm vllm

Tue, 02 Dec 2025 15:15:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Tue, 02 Dec 2025 12:30:00 +0000

Type Values Removed Values Added
First Time appeared Vllm-project
Vllm-project vllm
Vendors & Products Vllm-project
Vllm-project vllm

Mon, 01 Dec 2025 23:00:00 +0000

Type Values Removed Values Added
Description vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.
Title vLLM vulnerable to remote code execution via transformers_utils/get_config
Weaknesses CWE-94
References
Metrics cvssV3_1

{'score': 7.1, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H'}

Subscriptions

Vllm Vllm
Vllm-project Vllm
cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2025-12-02T14:14:58.324Z

Reserved: 2025-12-01T18:22:06.865Z

Link: CVE-2025-66448

cve-icon Vulnrichment

Updated: 2025-12-02T14:14:54.375Z

cve-icon NVD

Status : Analyzed

Published: 2025-12-01T23:15:54.213

Modified: 2025-12-03T17:52:26.280

Link: CVE-2025-66448

cve-icon Redhat

Severity : Important

Publid Date: 2025-12-01T22:45:42Z

Links: CVE-2025-66448 - Bugzilla

cve-icon OpenCVE Enrichment

Updated: 2025-12-02T11:58:51Z

Weaknesses