Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

redhat логотип

CVE-2026-55514

Опубликовано: 06 июл. 2026
Источник: redhat
CVSS3: 6.5
EPSS Низкий

Описание

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.

A flaw was found in vLLM, a library for Large Language Model (LLM) inference and serving. A remote attacker, authorized to make a /v1/completions request, can send a specially crafted prompt embeds payload. This action causes the EngineCore to fail an assertion and fatally crash, leading to a Denial of Service (DoS) for the entire server application.

Отчет

This Moderate-impact flaw in vLLM, as used in Red Hat AI Inference Server, Red Hat OpenShift AI, and Red Hat Enterprise Linux AI, allows a remote, authenticated attacker to trigger a denial of service. By sending a specially crafted prompt embeds payload to the /v1/completions endpoint with a model utilizing M-RoPE, the attacker can cause the EngineCore to crash, leading to the unavailability of the server application. This issue requires prior authorization to make requests to the /v1/completions endpoint.

Меры по смягчению последствий

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

Затронутые пакеты

ПлатформаПакетСостояниеРекомендацияРелиз
Red Hat AI Inference Serverrhaiis/vllm-cpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaiis/vllm-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaiis/vllm-neuron-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-rocm-rhel9Fix deferred
Red Hat AI Inference Serverrhaiis/vllm-spyre-rhel9Not affected
Red Hat AI Inference Serverrhaiis/vllm-tpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-cpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-gaudi-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-neuron-rhel9Fix deferred

Показывать по

Дополнительная информация

Статус:

Moderate
Дефект:
CWE-617
https://bugzilla.redhat.com/show_bug.cgi?id=2497504vllm: vLLM: Denial of Service via crafted prompt in /v1/completions request

EPSS

Процентиль: 30%
0.0037
Низкий

6.5 Medium

CVSS3

Связанные уязвимости

CVSS3: 6.5
nvd
29 дней назад

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.

CVSS3: 6.5
debian
29 дней назад

vLLM is a library for LLM inference and serving. From 0.12.0 to before ...

github
15 дней назад

vLLM denial of service via prompt embeds on M-RoPE models

EPSS

Процентиль: 30%
0.0037
Низкий

6.5 Medium

CVSS3