{"id":"CVE-2025-29783","aliases":["EUVD-2025-6725","GHSA-x3m8-f7g5-qhm7","PYSEC-2025-63"],"status":"published","title":"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.","severity":{"version":"3.1","score":9.1,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","level":"critical","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00734,"percentile":0.54744,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-502"],"published":"2025-03-19T15:33:28Z","modified":"2026-10-28T02:30:36Z","fixes":[{"ecosystem":"PyPI","package":"vllm","fixed_in":["0.8.0"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.6.5"},{"fixed":"0.8.0"}]}]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.6.5"},{"fixed":"0.8.0"}]}],"versions":["0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3"]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"GIT","events":[{"introduced":"0"},{"fixed":"288ca110f68d23909728627d3100e5a8db820aa2"}]},{"type":"ECOSYSTEM","events":[{"introduced":"0.6.5"},{"fixed":"0.8.0"}]}],"versions":["0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3"]}],"products":[{"vendor":"vllm","product":"vllm"},{"vendor":"vllm-project","product":"vllm"}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7","tags":["x_refsource_CONFIRM","Vendor Advisory","advisory","web"]},{"url":"https://github.com/vllm-project/vllm/pull/14228","tags":["x_refsource_MISC","Issue Tracking","Vendor Advisory","fix","web","report"]},{"url":"https://github.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-29783","tags":["advisory"]},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-63.yaml","tags":["web"]},{"url":"https://github.com/advisories/GHSA-x3m8-f7g5-qhm7"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/29xxx/CVE-2025-29783.json","tags":["advisory"]},{"url":"https://github.com/vllm-project/vllm","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2025-29783","title":"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.","status":"published","published":"2025-03-19T15:33:28.951Z","modified":"2025-03-22T00:02:54.404Z","cvss":[{"version":"3.1","score":9.1,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","level":"critical","assessor":"cna"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T14:32:45.797843Z"}],"euvd":[{"id":"EUVD-2025-6725","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.","status":"published","published":"2025-03-19T15:33:28Z","modified":"2025-03-22T00:02:54Z","cvss":[{"version":"3.1","score":9.1,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","level":"critical"}],"updated_at":"2026-11-02T20:52:55.622908Z"}],"ghsa":[{"id":"GHSA-x3m8-f7g5-qhm7","title":"vLLM Allows Remote Code Execution via Mooncake Integration","description":"### 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","status":"published","published":"2025-03-19T15:55:58Z","modified":"2025-07-02T14:20:40Z","cvss":[{"version":"3.1","score":9,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","level":"critical"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T14:38:48.783737Z"}],"nvd":[{"id":"CVE-2025-29783","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.","status":"published","published":"2025-03-19T16:15:32.477Z","modified":"2026-06-17T09:05:39.83Z","cvss":[{"version":"3.1","score":9,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","level":"critical","assessor":"secondary"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T14:10:54.744127Z"}],"osv":[{"id":"CVE-2025-29783","title":"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.","status":"published","published":"2025-03-19T15:33:28.951Z","modified":"2026-10-28T02:30:36.996017384Z","cvss":[{"version":"3.1","score":9,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","level":"critical"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T15:44:47.708311Z"},{"id":"GHSA-x3m8-f7g5-qhm7","title":"vLLM Allows Remote Code Execution via Mooncake Integration","description":"### 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","status":"published","published":"2025-03-19T15:55:58Z","modified":"2026-08-07T08:11:55.81267503Z","cvss":[{"version":"3.1","score":9,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","level":"critical"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T15:46:59.484835Z"},{"id":"PYSEC-2025-63","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.","status":"published","published":"2025-03-19T16:15:32Z","modified":"2025-07-01T23:59:56.271533Z","updated_at":"2026-11-02T15:52:54.242332Z"}]}}