8.8 High

CVE-2026-116176 vLLM 0.9.2 before 0.24.0 SSRF via X-Request-Id in P2pNcclConnector

Description

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.

CVSS 4.0 detail

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:L/SC:N/SI:N/SA:N

Exploitable remotely over the network, without an account and without any user action; an attacker can seriously compromise confidentiality, integrity or availability.

Attack vector: Network
Attack complexity: Low
Attack requirements: None
Privileges required: None
Interaction: None
Confidentiality: High
Integrity: None
Availability: Low
Confidentiality of other systems: None
Integrity of other systems: None
Availability of other systems: None

Affected products and versions

Product	Affected versions	Fixed in
vllm 0.24	earliest → < 0.24.0	0.24.0
vllm 0.9	0.9.2 → < 0.24.0	0.24.0

References

GitHub Security Advisory (GHSA-vfp2-c8pq-v6h6) github.com
VulnCheck Advisory: vLLM 0.9.2 before 0.24.0 SSRF via X-Request-Id in P2pNcclConnector www.vulncheck.com

Timeline

Published October 25, 2026
Last modified November 4, 2026

The 121 CVEs of vllm →

CVE-2026-115918 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115917 vLLM is an inference and serving engine for large language models 3.4 Low CVE-2026-115916 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115915 vLLM is an inference and serving engine for large language models 8.1 High

Track this CVE