Arbitrary Code Injection Affecting vllm package, versions [,0.11.1)
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applicationsSnyk Learn
Learn about Arbitrary Code Injection vulnerabilities in an interactive lesson.
Start learning- Snyk IDSNYK-PYTHON-VLLM-14157153
- published2 Dec 2025
- disclosed1 Dec 2025
- creditSong Liu
Introduced: 1 Dec 2025
CVE-2025-66448 (opens in a new tab)How to fix?
Upgrade vllm to version 0.11.1 or higher.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Arbitrary Code Injection via the config class named Nemotron_Nano_VL_Config. An attacker can execute arbitrary code on the host system by publishing a repository with a crafted configuration that references a malicious backend through the auto_map field, which is then fetched and executed even if remote code execution is explicitly disabled.