8.8

CVSS Score

3.1

-

CVSS Score

Basic Information

Concerned about an active attack path?

Talk to our security experts and see Miggo in action.

Miggo Vulnerability Database

→

CVE-2025-67729

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.

(GitHub Advisory)

Miggo Vulnerability Database

→

CVE-2025-67729

CVE-2025-67729:

8.8

CVSS Score

3.1

-

CVSS Score

Basic Information

Is this CVE running in your environment?

Easily map the attack path and prioritize which CVEs are a threat to your organization

Validate Exposure

Technical Details

Package Name	Ecosystem	Vulnerable Versions	First Patched Version
lmdeploy	pip	<= 0.11	0.11.1

Technical Details

Vulnerability Intelligence
Miggo AI

Root Cause Analysis

The vulnerability exists because the lmdeploy library uses torch.load() to deserialize model files from sources that may not be trusted. The torch.load function internally uses Python's pickle module, which is known to be insecure for loading data from untrusted sources as it can execute arbitrary code. The vulnerability is present in multiple locations where model weights or statistics are loaded from .bin or .pth files. An attacker could craft a malicious model file containing a payload that executes arbitrary commands on the victim's machine when the file is loaded by lmdeploy. The fix, applied in commit eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee, is to add the weights_only=True parameter to all torch.load() calls. This parameter ensures that only the model's tensors (weights) are loaded, preventing the execution of any potentially malicious code embedded in the file.

Vulnerable functions

Only Mi**o us*rs **n s** t*is s**tion

Vulnerability Intelligence
Miggo AI

Unlock WAF rules for this CVE

Generate vendor-ready rules for the observed attack patterns, plus reasoning and safe deployment guidance

Get WAF rules

WAF Protection Rules

WAF Rule

W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.

Reasoning

*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.