CVE-2025-29783

vLLM Allows Remote Code Execution via Mooncake Integration

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.

Scores

Weaknesses (CWE)

• CWE-502

Advisories

• GHSA-x3m8-f7g5-qhm7 — vLLM Allows Remote Code Execution via Mooncake Integration
• PYSEC-2025-63 — vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed di

European references

• ENISA EUVD · EUVD-2025-6725
• GCVE · GCVE-0-2025-29783

Affected configurations (NVD CPE)

• cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.6.5 < 0.8.0

Affected products

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7
• https://github.com/vllm-project/vllm/pull/14228
• https://github.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2

Sources