CVE-2025-29783
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.
- Score
- CVSS 3.1 9.1 Critical
- Status
- Analyzed - security-advisories@github.com
- Published
- 2025-03-19
- Last modified
- 2025-03-22
- Weaknesses
- CWE-502
Affected products
- Vllm (Vllm)
- Vllm (Vllm-project)
References
- https://github.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2
- https://github.com/vllm-project/vllm/pull/14228
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7
