AUGUST 21, 2026
Live Feed
Back to database
Case File

CVE-2026-55514

MEDIUM · CVSS 6.5 EPSS 0.37% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-07-06 · Last synced 2026-08-05

CyberRota Analysis

AI-Generated

The vLLM library versions from 0.12.0 to before 0.24.0 are vulnerable to a flaw that allows authorized remote users to send a specially crafted prompt in a /v1/completions request, leading to a fatal crash of the EngineCore and shutting down the server application. Organizations utilizing this library for LLM inference and serving should prioritize upgrading to version 0.24.0 to mitigate the risk of service disruption.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-55514
Severity
MEDIUM
CVSS
6.5
EPSS
0.37%

Original NVD Description

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.

Related CVEs

Other vulnerabilities affecting the same vendor(s)