Vulnerability · Published Sep 16, 2026 · Assigned by GitHub_M
CVE-2025-59953LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy
Critical 9.8
In plain English
A critical-severity unsafe deserialization in lmdeploy from InternLM. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.9% (higher than 59% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | lmdeploy | 0.10.2 | GHSA-5h8j-6crg-7rmw |
| PyPI | lmdeploy | 0.10.2 | PYSEC-2026-4079 |
Affected products (as reported)
Weakness: CWE-502 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
References
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw x_refsource_CONFIRM
- https://github.com/InternLM/lmdeploy/releases/tag/v0.10.2 x_refsource_MISC