Description
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.
CVSS Metrics
- Vector
- CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
- Attack Vector
- adjacent network
- Complexity
- low
- Privileges
- low
- User Action
- none
- Scope
- changed
- Confidentiality
- high
- Integrity
- high
- Availability
- high
- Weaknesses
- CWE-502
Metadata
- Primary Vendor
- VLLM
- Published
- 3/19/2025
- Last Modified
- 7/1/2025
- Source
- NIST NVD
- Note: Verify all details with official vendor sources before applying patches.
Affected Products
vllm : vllm
AI-Powered Remediation
Generate remediation guidance or a C-suite brief for this vulnerability.