Most recent entries from all

bdu:2026-03420

certfr-2025-avi-1057 — De multiples vulnérabilités ont été découvertes dans les produits VMware. Elles permettent à un attaquant de provoquer…

certfr-2025-avi-1057

EUVD-2026-240377

fkie_cve-2025-47277

vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the `PyNcclCommunicator` class, while CPU-side control message passing is handled via the `send_obj` and `recv_obj` methods on the CPU side. The intention was that this interface should only be exposed to a private network using the IP address specified by the `--kv-ip` CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the `TCPStore` interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the `TCPStore` instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the `TCPStore` socket to the private interface as configured.

GHSA-hjq4-87xh-g4fv — vLLM Allows Remote Code Execution via PyNcclPipe Communication Service

Affected: PyPI: vllm

### Impacted Environments

This issue ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected.

### Summary vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the `PyNcclCommunicator` class, while CPU-side control message passing is handled via the `send_obj` and `recv_obj` methods on the CPU side.

A remote code execution vulnerability exists in the `PyNcclPipe` service. Attackers can exploit this by sending malicious serialized data to gain server control privileges.

The intention was that this interface should only be exposed to a private network using the IP address specified by the `--kv-ip` CLI parameter. The vLLM documentation covers how this must be limited to a secured network: https://docs.vllm.ai/en/latest/deployment/security.html

Unfortunately, the default behavior from PyTorch is that the `TCPStore` interface will listen on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the `TCPStore` instance to bind its socket to a specified private interface.

This issue was reported privately to PyTorch and they determined that this behavior was intentional.

### Details The `PyNcclPipe` implementation contains a criti…

PYSEC-2026-567 — vLLM Allows Remote Code Execution via PyNcclPipe Communication Service

Affected: PyPI: vllm

### Impacted Environments

This issue ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected.

A remote code execution vulnerability exists in the `PyNcclPipe` service. Attackers can exploit this by sending malicious serialized data to gain server control privileges.

### Details The `PyNcclPipe` implementation contains a crit…

RHSA-2025:10403 — Red Hat Security Advisory: Red Hat AI Inference Server 3.0 (ROCm)

vllm: vLLM Allows Remote Code Execution via PyNcclPipe Communication Service

WID-SEC-W-2025-2883 — Red Hat Enterprise AI Inference Server (vLLM): Schwachstelle ermöglicht Codeausführung

Ein Angreifer aus einem angrenzenden Netzwerk kann eine Schwachstelle in Red Hat Enterprise AI Inference Server ausnutzen, um beliebigen Programmcode auszuführen.