{"id":"CVE-2025-66455","published":"2026-09-18T18:17:04.420","lastModified":"2026-09-23T18:12:04.247","description":"LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe.","cvssScore":9.8,"cvssSeverity":"CRITICAL","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","cwes":["CWE-502"],"vendors":[],"products":[],"references":[{"url":"https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2","tags":[]},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0","tags":[]},{"url":"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2","tags":[]}],"exploitRefs":[{"url":"https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2","tags":[]},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0","tags":[]},{"url":"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2","tags":[]}],"hasPoc":true,"ai":{"summary":"LMDeploy's PyTorch DistServe/PD-disaggregation control plane deserializes messages using Python pickle, allowing remote code execution if an attacker can reach the `/distserve/p2p_connect` endpoint.","exploitability":"Exploitation is relatively easy if an attacker can reach the `/distserve/p2p_connect` endpoint, which requires the DistServe API server to be exposed to untrusted clients.","blast_radius":"If exploited, this could result in unauthenticated remote code execution with the privileges of the LMDeploy serving process, potentially leading to full system compromise.","remediation":"Restrict access to the `/distserve/*` endpoints to trusted networks and enable API-key authentication. Upgrade to LMDeploy 0.16.0 or later.","detection":"No reliable host or network indicator is derivable from the published description.","tags":["rce","web","pickle","auth-bypass","zeromq","pytorch"],"model":"qwen2.5:7b-instruct","analyzedAt":"2026-09-27T09:01:56.684Z"}}