Server-side Request Forgery (SSRF) Affecting vllm package, versions [0.9.2,0.24.0)
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-21707826
- published25 Oct 2026
- disclosed25 Oct 2026
- creditmschwarzl
Introduced: 25 Oct 2026
NewCVE-2026-116176 (opens in a new tab)How to fix?
Upgrade vllm to version 0.24.0 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 the P2pNcclConnector KV cache transfer connector, which exposes KV cache contents to network-accessible peers without adequate access control. An unauthenticated remote attacker can read KV cache data transferred between prefill and decode instances, leading to disclosure of cached model inference data and a partial availability impact on the transfer pipeline.
Note: This is only exploitable when the P2pNcclConnector is explicitly configured as the KV transfer connector.