CVE-2025-48956

7.5 HIGH
Published: August 21, 2025 Modified: October 09, 2025

Description

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.

AI Explanation

Get an AI-powered plain-language explanation of this vulnerability and remediation steps.

Login to generate AI explanation

CVSS v3.x Details

0.0 Low Medium High Critical 10.0
Vector String
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References to Advisories, Solutions, and Tools

Patch Vendor Advisory Exploit Third Party Advisory
https://github.com/vllm-project/vllm/pull/23267
Source: security-advisories@github.com
Issue Tracking Patch
https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47
Source: security-advisories@github.com
Vendor Advisory

3 reference(s) from NVD

Quick Stats

CVSS v3 Score
7.5 / 10.0
EPSS (Exploit Probability)
0.4%
62th percentile
Exploitation Status
Not in CISA KEV

Weaknesses (CWE)

Affected Vendors

vllm