CVE-2025-66448: vllm Code Injection — Fix

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.

Is your site exposed to CVE-2025-66448?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

7.1

HIGH

CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H

Weakness Type (CWE)

CWE-94 CWE-94

Affected Products

Vendor	Product	Versions
vllm	vllm	< 0.11.1

References

Advisories & Patches

https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86 https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm

Other References

https://github.com/vllm-project/vllm/pull/28126

Frequently Asked Questions

What is CVE-2025-66448? +

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. It has a CVSS v3.1 base score of 7.1 (HIGH).

How severe is CVE-2025-66448? +

CVE-2025-66448 has a CVSS v3.1 score of 7.1 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching.

What products are affected by CVE-2025-66448? +

CVE-2025-66448 affects products from vllm, specifically: vllm. Check the affected products table above for specific version ranges.

How do I check if I'm vulnerable to CVE-2025-66448? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2025-22136

Tabby (formerly Terminus) is a highly configurable terminal emulator. Prior to 1.0.217 , Tabby enables several high-risk Electron Fuses, including …

CVE-2025-24482

A Local Code Injection Vulnerability exists in the product and version listed above. The vulnerability is due to incorrect default …

CVE-2026-42890

Actual is an open-source personal finance application. In the macOS desktop application version 25.x (built on Electron 39.2.7), the ELECTRON_RUN_AS_NODE …

CVE-2026-53511

calibre is an e-book manager. Prior to 9.10.0, a malicious EPUB, OPF, or PDF file can execute arbitrary Python code …

CVE-2026-43921

FOSSBilling is a free, open-source billing and client management system. Versions 0.6.10 through 0.7.2 have a PHP code injection vulnerability …

CVE-2025-24959

zx is a tool for writing better scripts. An attacker with control over environment variable values can inject unintended environment …

CVE-2025-66448