Deserialization in Internlm Lmdeploy
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.
Vulnerability class: Insecure Deserialization
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
Affected products
- Internlm Lmdeploy — versions >= 0.9.1, < 0.10.2
Weakness classification (CWE)
References
- security-advisories@github.com (x_refsource_CONFIRM)
- security-advisories@github.com (x_refsource_MISC)
Frequently asked questions
- What is CVE-2025-59953?
- CVE-2025-59953 is a critical-severity vulnerability in Internlm Lmdeploy, classified under Deserialization of Untrusted Data. CVSS score: 9.8/10. Published 2026-09-16.
- How severe is CVE-2025-59953?
- Critical severity. CVSS v3 base score is 9.8 out of 10.