CVE-2026-94624

A flaw was found in vLLM. A remote attacker can exploit a denial of service vulnerability in the P2P KV offloading mechanism. By supplying arbitrary remote host and port values, an attacker can create unreachable peer sessions that consume ZeroMQ sockets. This resource exhaustion leads to an...

Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration

Affected EnvironmentsNote that this issue only affects the V0 engine, which has been off by default since v0.8.0. Further, the issue only applies to a deployment using tensor parallelism across multiple hosts, which we do not expect to be a common deployment pattern.Since V0 is has been off by...

EUVD-2025-13625

Malicious code in bioql PyPI...

CVE-2025-30165 Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration

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 ...

PYSEC-2025-42

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 vulnerab...

CVE-2025-32444

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 vulnerab...

PYSEC-2025-42

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 vulnerab...

CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration

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 vulnerab...

CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration

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 vulnerab...

CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration

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 vulnerab...

PT-2025-18216

Name of the Vulnerable Software and Affected Versions vLLM versions 0.6.5 through 0.8.4 Description vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The issue concerns the use of pickle-based serialization over unsecured ZeroMQ sockets when vLLM is integrated...

PT-2024-33890

Name of the Vulnerable Software and Affected Versions Llama Stack versions prior to revision 7a8aa775e5a267cf8660d83140011a0b7f91e005 Meta Llama Framework affected versions not specified Description Llama Stack, prior to revision 7a8aa775e5a267cf8660d83140011a0b7f91e005, used Pickle as a...