Описание
vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.
A flaw was found in vLLM, an inference and serving engine for large language models (LLMs). This vulnerability allows unauthenticated attackers to cause a Denial of Service (DoS) by supplying image or video placeholder sequences without matching data, leading to an unhandled error and worker termination. Additionally, text-only prompts containing special tokens can be misinterpreted as control commands, potentially leading to unexpected behavior.
Отчет
This is an Important denial of service vulnerability affecting vLLM, as integrated into Red Hat AI Inference Server, Red Hat OpenShift AI, and Red Hat Enterprise Linux AI. The flaw allows unauthenticated attackers to trigger worker termination and degrade service availability by submitting malformed multimodal input or text prompts containing specific token sequences. This impact is significant due to the potential for service disruption in AI inference workloads.
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
| Платформа | Пакет | Состояние | Рекомендация | Релиз |
|---|---|---|---|---|
| Red Hat AI Inference Server | rhaiis/vllm-cpu-rhel9 | Will not fix | ||
| Red Hat AI Inference Server | rhaiis/vllm-cuda-rhel9 | Affected | ||
| Red Hat AI Inference Server | rhaiis/vllm-neuron-rhel9 | Will not fix | ||
| Red Hat AI Inference Server | rhaiis/vllm-rocm-rhel9 | Affected | ||
| Red Hat AI Inference Server | rhaiis/vllm-spyre-rhel9 | Affected | ||
| Red Hat AI Inference Server | rhaiis/vllm-tpu-rhel9 | Will not fix | ||
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-aws-cuda-rhel9 | Affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-azure-cuda-rhel9 | Affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-azure-rocm-rhel9 | Affected | ||
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-cuda-rhel9 | Affected |
Показывать по
Дополнительная информация
Статус:
7.5 High
CVSS3
Связанные уязвимости
vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.
vLLM is an inference and serving engine for large language models (LLM ...
vLLM Vulnerable to Remote DoS via Special-Token Placeholders
7.5 High
CVSS3