VULNERABILITY INTELLIGENCE

CVE-2025-48956

CVSS score7.5 HIGH
EPSS probability0.56%
CISA KEVNot currently listed
Published2025-08-21
Last modified2026-06-17
CVSS vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

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.

Weakness classification

  • security-advisories@github.com: CWE-400

Primary references