Server-side Request Forgery (SSRF) Affecting vllm package, versions [0.14.1,0.17.0)
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 Server-side Request Forgery (SSRF) vulnerabilities in an interactive lesson.
Start learning- Snyk IDSNYK-PYTHON-VLLM-15443354
- published10 Mar 2026
- disclosed9 Mar 2026
- creditRacerZ-fighting
Introduced: 9 Mar 2026
CVE-2026-25960 (opens in a new tab)How to fix?
Upgrade vllm to version 0.17.0 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 Server-side Request Forgery (SSRF) via inconsistent URL parsing between the validation layer and the HTTP client in the load_from_url and load_from_url_async functions. An attacker can access internal network resources or sensitive endpoints by supplying specially crafted URLs that bypass validation.