Arbitrary Code Injection Affecting vllm package, versions [0.10.1,0.14.0)
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-15057973
- published22 Jan 2026
- disclosed21 Jan 2026
- creditbugbunny.ai
Introduced: 21 Jan 2026
CVE-2026-22807 (opens in a new tab)How to fix?
Upgrade vllm to version 0.14.0 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 auto_map process during model initialization, even when trust_remote_code is false. An attacker can execute arbitrary code on the host system by supplying a malicious model repository or path that contains attacker-controlled Python code, which is loaded and executed during the model resolution phase.