{"id":"CVE-2025-66455","title":"LMDeploy is a toolkit for compressing, deploying, and serving large language models","summary":"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 m…","severity":"critical","cvss":9.8,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","cwe":["CWE-502"],"vendor":"InternLM","product":"lmdeploy","affected":["lmdeploy >= 0.9.2, < 0.16.0"],"patched":["lmdeploy 0.16.0"],"published":"2026-09-18","updated":"2026-09-23","sourceUpdated":"2026-09-23T18:12:04.247","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2025-66455","references":[{"url":"https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2","label":"security-advisories@github.com"},{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0","label":"security-advisories@github.com"},{"url":"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2","label":"security-advisories@github.com"},{"url":"https://github.com/advisories/GHSA-2vh9-42vm-xmv2"},{"url":"https://github.com/InternLM/lmdeploy"}],"tags":["nvd","cve.org","ghsa","pip","osv"],"epss":0.00702,"epssPercentile":0.51834,"aliases":["GHSA-2vh9-42vm-xmv2"],"ecosystem":"pip","ssvc":{"exploitation":"none","automatable":"yes","technicalImpact":"total","timestamp":"2026-09-18T19:54:08.825899Z"},"ingestedAt":"2026-09-18T17:46:41.532Z","slug":"CVE-2025-66455","body":"## Overview\n\nLMDeploy 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.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.\n\n## Package advisory (CVE-2025-66455)\n\nAffected packages:\n\n- `lmdeploy >= 0.9.2, < 0.16.0`\n\nPatched in:\n\n- `lmdeploy 0.16.0`\n\nSource: https://github.com/advisories/GHSA-2vh9-42vm-xmv2","depth":"midnight","depthScore":54,"depthScoreParts":{"impact":53.9,"likelihood":0.1,"exploitation":0,"ransomware":0},"changes":[]}