Home

Description

LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weights_only=True parameter when loading model checkpoint files. This allows an attacker to execute arbitrary code on the victim's machine when they load a malicious .bin or .pt model file. This issue has been patched in version 0.11.1.

PUBLISHED Reserved 2025-12-10 | Published 2025-12-26 | Updated 2025-12-26 | Assigner GitHub_M




HIGH: 8.8CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Problem types

CWE-502: Deserialization of Untrusted Data

Product status

< 0.11.1
affected

References

github.com/...deploy/security/advisories/GHSA-9pf3-7rrr-x5jh exploit

github.com/...deploy/security/advisories/GHSA-9pf3-7rrr-x5jh

github.com/...ommit/eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee

cve.org (CVE-2025-67729)

nvd.nist.gov (CVE-2025-67729)

Download JSON

Data based on CVE®. Copyright © 1999-2025, The MITRE Corporation. All rights reserved.