CVE-2026-24220

CVE-2026-24220 affects NVIDIA TensorRT-LLM across platforms. The vulnerability lies in the visual gen server, enabling unsafe deserialization through unauthorized ZeroMQ deserialization, which could lead to code execution. The CVSS v3.1 metrics indicate a local attack with high privileges require...

CVE-2025-30165

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 ...

CVE-2025-30165

CVE-2025-30165 : In multi-node vLLM deployments using the V0 engine, a secondary host opens a SUB socket and deserializes inbound data with Python’s unsafe pickle over ZeroMQ XPUB/SUB, enabling remote code execution. The issue affects V0 deployments with tensor parallelism across hosts; V1 is una...