CRITICAL🇵🇱 Wersja polska

CVE-2025-29783

CVSS 9.0v3.1pub. 2025-03-19upd. 2025-07-01

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 impacting any deployments using Mooncake to distribute KV across distributed hosts. This vulnerability is fixed in 0.8.0.

🤖 AI Analysis
How it works

When vLLM is configured with Mooncake integration (used to distribute KV cache memory across hosts), data transmitted over the ZMQ/TCP protocol is deserialized in an unsafe manner without proper validation or authentication. An attacker with access to the local network (attack vector AV:A) can send a crafted payload to the listening ZMQ/TCP socket, resulting in arbitrary code execution on the target host. The scope of the vulnerability covers all network interfaces on which the service operates.

Impact

An attacker can gain full control over the compromised host — achieving confidentiality, integrity, and availability at a critical level (C:H/I:H/A:H) — and potentially spread to other nodes in the distributed infrastructure.

Mitigation & patch

Update vLLM to version 0.8.0 or later, where the vulnerability has been removed. Additionally, until the patch is deployed, it is recommended to isolate vLLM hosts at the network level (firewall, network segmentation) so that ZMQ/TCP ports are inaccessible from untrusted network segments.

Who is affected

All vLLM deployments using Mooncake integration for distributing KV cache memory across distributed hosts, in versions prior to 0.8.0.

Analysis generated by Claude AI (Anthropic) based on NVD data. Always verify with vendor.
CVSS Vector
CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
  • Vllm

    APP
    Vllm
    0.6.5 – 0.8.0 (excl.)
🔵
CHECK WITH VENDOR
No clear patch data available. Check vendor references.
Tags
RCEDeserialization
CWE
References

Related vulnerabilities

CVE-2026-48746CRITICAL9.1PL ✓same product

Pominięcie uwierzytelnienia w vLLM — bypass klucza API OpenAI

CVE-2026-22778CRITICAL9.8PL ✓same product

vLLM: wyciek adresu sterty umożliwiający RCE przez endpoint multimodalny

CVE-2025-47277CRITICAL9.8PL ✓same product

vLLM: niezamierzone nasłuchiwanie TCPStore na wszystkich interfejsach sieciowych

CVE-2025-32444CRITICAL10.0PL ✓same product

RCE w vLLM poprzez deserializację pickle na niezabezpieczonych gniazdach ZeroMQ

CVE-2024-11041CRITICAL9.8PL ✓same product

RCE przez niebezpieczną deserializację w vllm MessageQueue.dequeue()