CVE-2025-67729
HIGH EPSS 38.3%
Published Dec 26, 20256mo ago · Modified Jun 17, 20261w ago
8.8 CVSS 3.1
Published Dec 26, 2025 6mo ago
Last Modified Jun 17, 2026 1w ago
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 Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction Required
Scope Unchanged
Confidentiality High
Integrity High
Availability High
Threat Intelligence
EPSS Exploit Probability
38.3% percentile
Exploit & Patch Status
No Known Exploit
Patch Available
Weaknesses 1
CWE-502 Deserialization of Untrusted Data Validation
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| internlm | lmdeploy | * | <0.11.1 |
References 2
- github.com https://github.com/InternLM/lmdeploy/commit/eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee
- github.com https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh
Remediation
- github.com https://github.com/InternLM/lmdeploy/commit/eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee