CVE 検索
公開されているすべての CVE とオープンソースのセキュリティアドバイザリ（NVD、OSV、GitHub）を、CVSS、EPSS、実際に悪用されているか（CISA KEV）とともに掲載しています。数時間ごとに更新されます。スキャンでは、検出した技術とこれらを照合します。
公開されているすべての CVE とオープンソースのセキュリティアドバイザリ（NVD、OSV、GitHub）を、CVSS、EPSS、実際に悪用されているか（CISA KEV）とともに掲載しています。数時間ごとに更新されます。スキャンでは、検出した技術とこれらを照合します。
| 20/05/2025 |
| CVE-2025-30165 | 高8.0 | vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a `SUB` ZeroMQ socket and connect to an `XPUB` socket on the primary vLLM host. When data is received on this | 06/05/2025 |
| CVE-2025-46560 | 高7.5 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|i | 30/04/2025 |
| CVE-2025-32444 | 緊急9.8 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were set to | 30/04/2025 |
| CVE-2025-30202 | 高7.5 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purpos | 30/04/2025 |
| CVE-2024-11041 | 緊急9.8 | vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload to the MessageQueue, causing the victim's | 20/03/2025 |
| CVE-2025-29783 | 緊急9.0 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code execution vulnerability im | 19/03/2025 |
| CVE-2025-29770 | 中6.5 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output (a.k.a. guided decoding). Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default i | 19/03/2025 |
| CVE-2025-25183 | 低2.6 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-in hash() function. As o | 07/02/2025 |
| CVE-2025-24357 | 高8.8 | vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it | 27/01/2025 |