CVE-2026-55514

What it is

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.

At a glance

Exploitability

Can be exploited over the network with a low-privilege account. High risk of service disruption.

Exploit odds

0.7% chance of exploitation in the next 30 days (EPSS).

Fix

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

Timeline

1. 2026-07-06 21:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-10-25 20:10 UTC Last updatedMost recent change to the record

Why it ranks here

• Exploited in the wild: no, CISA does not list it.
• Exploit odds: 0.7% in the next 30 days (EPSS).
• Severity: 7.1 HIGH (CVSS).
• Fix: a patch or advisory is linked.

Details

Published

2026-07-06 21:16 UTC

Last modified

2026-10-25 20:10 UTC

Exploit probability

0.7% · EPSS, next 30 days

Weakness

CWE-617

Record status

Analyzed

Affected

• Vllm < 0.24.0

Attack profile CVSS 4.0 · 7.1

Attack vector

Network

Complexity

Low

Attack requirements

None

Privileges needed

Low

User interaction

None

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-2026-55514.md and follow it. Check whether this project is affected by CVE-2026-55514. 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