Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-55514— vLLM denial of service via prompt embeds on M-RoPE models

Quick assessment

Affected
vllm-project vllm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.12.0版本至0.24.0之前版本存在异常处理不当漏洞，该漏洞源于向 /v1/completions 请求中发送纯提示嵌入有效载荷，会导致 EngineCore 断言失败并崩溃，造成远程授权用户可使服务器应用程序关闭。

AI Predicted 7.5 Difficulty: Easy EPSS 0.66% · P50

Possible ATT&CK Techniques 1 AI

T1499 · Endpoint Denial of Service

Affected Version Matrix 1

VendorProduct Version RangeStatus
vllm-project vllm >= 0.12.0, < 0.24.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-55514

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM denial of service via prompt embeds on M-RoPE models
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
Source: CVE Program / CVE List V5
Vulnerability Type
可达断言
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 异常处理不当漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.12.0版本至0.24.0之前版本存在异常处理不当漏洞，该漏洞源于向 /v1/completions 请求中发送纯提示嵌入有效载荷，会导致 EngineCore 断言失败并崩溃，造成远程授权用户可使服务器应用程序关闭。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vllm >= 0.12.0, < 0.24.0 -

II. Public POCs for CVE-2026-55514

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-55514

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-55514 (2)

Vendor Advisories for CVE-2026-55514 (1)

Other References for CVE-2026-55514 (1)

Same Patch Batch · vllm-project · 2026-07-06 · 4 CVEs total

CVE-2026-54234 7.5 HIGH vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection
CVE-2026-55646 6.5 MEDIUM vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size li
CVE-2026-55574 vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-617

V. Comments for CVE-2026-55514

No comments yet

Leave a comment