MISFIRE

Browse / Unsafe Model Loading and Supply Chain / CVE-2025-29783

vLLM Allows Remote Code Execution via Mooncake Integration

CVE-2025-29783 ยท 2025-03-19 critical

Class
Unsafe Model Loading and Supply Chain (filed by a model that read the source)
Technique
Unsafe deserialisation
Also involves
AI Framework and Platform Flaws
Affected
vllm (PyPI)
CVSS
CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
EPSS
0.7% chance of exploitation in 30 days

How it works, in short

vLLM's Mooncake KV-transfer pipe unpickles data received over a network socket, so a crafted payload sent to it runs code. (Our summary, written by a model. The source text is below.)

Details

Summary

When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP will allow attackers to execute remote code on distributed hosts.

Details

1. Pickle deserialization vulnerabilities are well documented. 2. The mooncake pipe is exposed over the network (by design to enable disaggregated prefilling across distributed environments) using ZMQ over TCP, greatly increasing exploitability. ~~Further, the mooncake integration opens these sockets listening on all interfaces on the host, meaning it can not be configured to only use a private, trusted network.~~

Only sender_socket and receiver_ack are allowed to be accessed publicly, while the data actually decompressed by pickle.loads() comes from recv_bytes. Its interface is defined as self.receiver_socket.connect(f\"tcp://{d_host}:{d_rank_offset + 1}\"), where d_host is decode_host, a locally defined address 192.168.0.139,from mooncake.json (https://github.com/kvcache-ai/Mooncake/blob/main/doc/en/vllm-integration-v0.2.md?plain=1#L36).

Impact

This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts.

Remediation

This issue is resolved by https://github.com/vllm-project/vllm/pull/14228

References

Source: GitHub Advisory Database, used under CC BY 4.0.