First published: Wed Mar 19 2025(Updated: )
### 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](https://docs.python.org/3/library/pickle.html). 2. The [mooncake pipe](https://github.com/vllm-project/vllm/blob/9bebc9512f9340e94579b9bd69cfdc452c4d5bb0/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L206) 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](https://github.com/vllm-project/vllm/blob/9bebc9512f9340e94579b9bd69cfdc452c4d5bb0/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L257). 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). 3. The root problem is [`recv_tensor()`](https://github.com/vllm-project/vllm/blob/9bebc9512f9340e94579b9bd69cfdc452c4d5bb0/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L257) calls [`_recv_impl`](https://github.com/vllm-project/vllm/blob/9bebc9512f9340e94579b9bd69cfdc452c4d5bb0/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L244) which passes the raw network bytes to `pickle.loads()`. Additionally, it does not appear that there are any controls (network, authentication, etc) to prevent arbitrary users from sending this payload to the affected service. ### 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
Credit: security-advisories@github.com
Affected Software | Affected Version | How to fix |
---|---|---|
vLLM | <0.8.0 | |
pip/vllm | >=0.6.5<0.8.0 | 0.8.0 |
Sign up to SecAlerts for real-time vulnerability data matched to your software, aggregated from hundreds of sources.
CVE-2025-29783 has a high severity due to the potential for remote code execution through unsafe deserialization.
To fix CVE-2025-29783, upgrade to vLLM version 0.8.0 or later where the vulnerability has been addressed.
CVE-2025-29783 affects all versions of vLLM prior to 0.8.0 that are configured to use Mooncake over ZMQ/TCP.
Attackers can execute remote code on distributed hosts due to the unsafe deserialization vulnerability in CVE-2025-29783.
CVE-2025-29783 is exposed over all network interfaces when vLLM is used with Mooncake, making it particularly vulnerable.