CVE-2025-59953

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server (AsyncRPCServer in zmq_rpc.py) for supporting the RPC communications. In its core functionality call_and_response(), I found it will directly use the pickles.loads() to deserialize the received messages without any sanitization, hence resulting in a remote code execution vulnerability by this RPC server. Version 0.10.2 contains a patch.

CVSS v3 9.8 CRITICAL

9.8^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 3.9 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/InternLM/lmdeploy/releases/tag/v0.10.2
https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw
https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw

Configurations

No configuration.

History

14 Oct 2026, 19:10

Type	Values Removed	Values Added
Summary		(es) LMDeploy es un kit de herramientas para comprimir, desplegar y servir modelos de lenguaje grandes. A partir de la versión 0.9.1 y versiones anteriores a la 0.10.2, LMDeploy implementa un servidor RPC (AsyncRPCServer en zmq_rpc.py) para soportar las comunicaciones RPC. En su funcionalidad principal call_and_response(), se descubrió que utiliza directamente pickles.loads() para deserializar los mensajes recibidos sin ninguna sanitización, lo que resulta en una vulnerabilidad de ejecución remota de código a través de este servidor RPC. La versión 0.10.2 contiene un parche.

18 Sep 2026, 18:17

Type	Values Removed	Values Added
References	~~() https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw -~~	() https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw -

16 Sep 2026, 16:17

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-09-16 16:17

Updated : 2026-10-14 19:10

NVD link : CVE-2025-59953

Mitre link : CVE-2025-59953

CVE.ORG link : CVE-2025-59953

JSON object : View

Products Affected

No product.

CWE

CWE-502

Deserialization of Untrusted Data

{"id": "CVE-2025-59953", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2025-59953", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "yes"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-09-18T18:05:34.211593Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 9.8, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 3.9}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "InternLM", "product": "lmdeploy", "versions": [{"status": "affected", "version": ">= 0.9.1, < 0.10.2"}]}]}], "published": "2026-09-16T16:17:03.010", "references": [{"url": "https://github.com/InternLM/lmdeploy/releases/tag/v0.10.2", "source": "security-advisories@github.com"}, {"url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw", "source": "security-advisories@github.com"}, {"url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Deferred", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-502"}]}], "descriptions": [{"lang": "en", "value": "LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy\u00a0implements an\u00a0rpc server (AsyncRPCServer in zmq_rpc.py)\u00a0for supporting the RPC communications. In its core functionality\u00a0call_and_response(), I found it will directly use the\u00a0pickles.loads()\u00a0to deserialize the received messages without any sanitization, hence resulting in a remote code execution vulnerability by this RPC server. Version 0.10.2 contains a patch."}, {"lang": "es", "value": "LMDeploy es un kit de herramientas para comprimir, desplegar y servir modelos de lenguaje grandes. A partir de la versi\u00f3n 0.9.1 y versiones anteriores a la 0.10.2, LMDeploy implementa un servidor RPC (AsyncRPCServer en zmq_rpc.py) para soportar las comunicaciones RPC. En su funcionalidad principal call_and_response(), se descubri\u00f3 que utiliza directamente pickles.loads() para deserializar los mensajes recibidos sin ninguna sanitizaci\u00f3n, lo que resulta en una vulnerabilidad de ejecuci\u00f3n remota de c\u00f3digo a trav\u00e9s de este servidor RPC. La versi\u00f3n 0.10.2 contiene un parche."}], "lastModified": "2026-10-14T19:10:00.297", "sourceIdentifier": "security-advisories@github.com"}