CVE-2025-48956 | Teknoloji dünyasından en güncel haberleri ve güvenlikle ilgili gelişmeleri takip edin.

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 triggere…
High CVSS: 7.5

CVE-2025-48956

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.
Vendor
Vllm
Product
Vllm
CWE
CWE-400
Yayın Tarihi
2025-08-21 15:15:32
Güncelleme
2025-10-09 18:04:53
Source Identifier
security-advisories@github.com
KEV Date Added
-

Kategoriler

CWE-400 Vllm HIGH Vllm 2025

Referanslar

https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944 https://github.com/vllm-project/vllm/pull/23267 https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47