LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py

Summary

CVECVE-2025-66455
StatePUBLISHED
AssignerGitHub_M
Source PriorityCVE Program / NVD first with legacy fallback
Published2026-09-18 18:17:04 UTC
Updated2026-09-18 20:17:00 UTC
DescriptionLMDeploy 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.

Risk And Classification

Primary CVSS: v3.1 9.8 CRITICAL from [email protected]

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS: 0.007020000 probability, percentile 0.514080000 (date 2026-09-21)

Problem Types: CWE-502 | CWE-502 CWE-502: Deserialization of Untrusted Data


VersionSourceTypeScoreSeverityVector
3.1[email protected]Secondary9.8CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
3.1CNADECLARED9.8CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS v3.1 Breakdown

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Vendor Declared Affected Products

SourceVendorProductVersionPlatforms
CNA InternLM Lmdeploy affected >= 0.9.2, < 0.16.0 Not specified

References

ReferenceSourceLinkTags
github.com/InternLM/lmdeploy/releases/tag/v0.16.0 [email protected] github.com
github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd992... [email protected] github.com
github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2 [email protected] github.com
CVE Program record CVE.ORG www.cve.org canonical
NVD vulnerability detail NVD nvd.nist.gov canonical, analysis

© CVE.report 2026

Use of this information constitutes acceptance for use in an AS IS condition. There are NO warranties, implied or otherwise, with regard to this information or its use. Any use of this information is at the user's risk. It is the responsibility of user to evaluate the accuracy, completeness or usefulness of any information, opinion, advice or other content. EACH USER WILL BE SOLELY RESPONSIBLE FOR ANY consequences of his or her direct or indirect use of this web site. ALL WARRANTIES OF ANY KIND ARE EXPRESSLY DISCLAIMED. This site will NOT BE LIABLE FOR ANY DIRECT, INDIRECT or any other kind of loss.

CVE, CWE, and OVAL are registred trademarks of The MITRE Corporation and the authoritative source of CVE content is MITRE's CVE web site. This site includes MITRE data granted under the following license.

Free CVE JSON API cve.report/api

CVE.report and Source URL Uptime Status status.cve.report