CVE-2025-48956 – vllm

Package

Manager: pip
Name: vllm
Vulnerable Version: >=0.1.0 <0.10.1.1

Severity

Level: High

CVSS v3.1: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

CVSS v4.0: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

EPSS: 0.00296 pctl0.52452

Details

vllm API endpoints vulnerable to Denial of Service Attacks ### Summary 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. ### Details The vulnerability leverages the abuse of HTTP headers. By setting a header such as `X-Forwarded-For` to a very large value like `("A" * 5_800_000_000)`, the server's HTTP parser or application logic may attempt to load the entire request into memory, overwhelming system resources. ### Impact _What kind of vulnerability is it? Who is impacted?_ Type of vulnerability: Denial of Service (DoS) ### Resolution Upgrade to a version of vLLM that includes appropriate HTTP limits by deafult, or use a proxy in front of vLLM which provides protection against this issue.

Metadata

Created: 2025-08-21T14:24:16Z
Modified: 2025-08-21T15:42:03Z
Source: https://github.com/github/advisory-database/blob/main/advisories/github-reviewed/2025/08/GHSA-rxc4-3w6r-4v47/GHSA-rxc4-3w6r-4v47.json
CWE IDs: ["CWE-400"]
Alternative ID: GHSA-rxc4-3w6r-4v47
Finding: F002
Auto approve: 1