{"id":"CVE-2025-29783","aliases":["GHSA-x3m8-f7g5-qhm7","PYSEC-2025-63"],"title":"vLLM Allows Remote Code Execution via Mooncake Integration","summary":"vLLM Allows Remote Code Execution via Mooncake Integration","severity":"critical","cvss":9,"cvssVector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","vendor":"vllm","product":"vllm","ecosystem":"pip","affected":["vllm >= 0.6.5, < 0.8.0"],"patched":["vllm 0.8.0"],"published":"2025-03-19","updated":"2026-08-07","source":"OSV","sourceUrl":"https://osv.dev/vulnerability/GHSA-x3m8-f7g5-qhm7","references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-29783"},{"url":"https://github.com/vllm-project/vllm/pull/14228"},{"url":"https://github.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2"},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-63.yaml"},{"url":"https://github.com/vllm-project/vllm"}],"tags":["osv","pip"],"epss":0.00728,"epssPercentile":0.5274,"ingestedAt":"2026-08-07T19:14:15.017Z","slug":"CVE-2025-29783","body":"## Overview\n\n### Summary\nWhen vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP will allow attackers to execute remote code on distributed hosts.\n\n### Details\n1. Pickle deserialization vulnerabilities are [well documented](https://docs.python.org/3/library/pickle.html).\n2. 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.~~\n\nOnly `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).\n\n3. 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.\n\n\n\n### Impact\nThis is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts.\n\n### Remediation\nThis issue is resolved by https://github.com/vllm-project/vllm/pull/14228\n\n## Affected packages\n\n- `vllm >= 0.6.5, < 0.8.0`\n\n## Remediation\n\nUpgrade to a patched release:\n\n- `vllm 0.8.0`","depth":"midnight","depthScore":50,"depthScoreParts":{"impact":49.5,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}