CVE-2025-48956

What it is

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.

At a glance

Exploitability

Can be exploited over the network without logging in. High risk of service disruption.

Exploit odds

0.6% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2025-08-21 15:15 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-06-17 09:30 UTC Last updatedMost recent change to the record

Why it ranks here

• Exploited in the wild: no, CISA does not list it.
• Exploit odds: 0.6% in the next 30 days (EPSS).
• Severity: 7.5 HIGH (CVSS).
• Fix: a patch or advisory is linked.

Details

Published

2025-08-21 15:15 UTC

Last modified

2026-06-17 09:30 UTC

Exploit probability

0.6% · EPSS, next 30 days

Weakness

CWE-400 · Uncontrolled resource consumption

Record status

Analyzed

Affected

• Vllm < 0.10.1.1

Attack profile CVSS 3.1 · 7.5

Attack vector

Network

Complexity

Low

Privileges needed

None

User interaction

None

Scope

Unchanged

Confidentiality

None

Integrity

None

Availability

High

Is it in your code?

Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.

Read https://cve-list.com/agent/cve/CVE-2025-48956.md and follow it. Check whether this project is affected by CVE-2025-48956. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.

Copy as ticket · More options · Status badge