CVE-2025-67729

lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()

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.

Affected

InternLM · lmdeploy

CVSS v3.1 GITHUB

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

EPSS

0.60% chance of exploitation in the next 30 days, 47th percentile

Published

2025-12-26

Proof-of-concept exploits (1)

• advisories/GHSA-9pf3-7rrr-x5jh

Security advisories

• InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh
• InternLM/lmdeploy/commit/eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee

References

• CVE Record
• NVD entry