VulnerabilityAnalyzed

CVE-2025-67729

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.

HIGH 8.8EPSS 0.60%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.60%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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.

CVSS 3.1: 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS: 0.60% probability · 47th percentile
CISA KEV: Not listed
Weakness: CWE-502
Affected: internlm/lmdeploy
Source: security-advisories@github.com

References

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.