---
id: "CVE-2026-116176"
kind: "vulnerability"
aliases: ["CVE-2026-116176"]
title: "vLLM: X-Request-Id header lets API callers force outbound connections"
severity: "high"
cvss: 8.8
epss: null
exploited: false
status: "open"
category: "ai-tooling"
products: []
ecosystems: []
tags: ["ai-inference", "ai-tooling", "python", "self-hosted", "vllm"]
not_affected_if: ["version-0.24.0-or-later"]
published_at: "2026-10-25T14:16:57+00:00"
first_seen_at: "2026-10-25T14:41:23+00:00"
updated_at: "2026-10-25T14:42:13+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-116176", "first_seen_at": "2026-10-25T14:41:23+00:00"}]
---

# vLLM: X-Request-Id header lets API callers force outbound connections

vLLM from 0.9.2 before 0.24.0 lets an API caller embed a decode address in the X-Request-Id header, forcing a P2pNcclConnector prefill worker to connect to an attacker-chosen host. An attacker can leak the NCCL unique_id and KV-cache tensors, or block the worker.

_Summary, check and fix written by a model from the sources; labelled as such._

## How to check

- Check the installed vLLM version with `pip show vllm` or `python -c "import vllm; print(vllm.__version__)"`
- Check whether disaggregated prefill with P2pNcclConnector is enabled in the serving configuration (unknown if the sources do not say how to find it)

## Fix

- Upgrade vLLM to `0.24.0` or later
- unknown for interim mitigations; the sources do not list any

## Timeline

- 2026-10-25T14:41:23+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-116176

## From the sources

vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by embedding a decode address in the X-Request-Id header. Attackers can make a P2pNcclConnector prefill worker ZMQ-connect to an attacker host, leaking the NCCL unique_id and KV-cache tensors or blocking the worker.

---

_Free to read at a human pace. An API with keys and an MCP server are in preparation; early access: hello@infrastack.ai_