Paper/Archive/CVE-2025-29783

CVE-2025-29783

vllm-project vllm — vLLM Allows Remote Code Execution via Mooncake Integration

Description · from the CVE record

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.

Affected

ProductAffectedFixed inSource
vllm>= 0.6.5, < 0.8.0–CNA

Scores by source

GitHub_M (CNA)9.1CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
CISA ADPSSVCExploitation: none · Automatable: yes · Technical impact: total

References

refgithub.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7refgithub.com/vllm-project/vllm/pull/14228refgithub.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2