CVE-2025-67729
HIGH
8,8
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: required
Scope: unchanged
Confidentiality: high
Integrity: high
Availability: high
Description
AI Translation Available
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.
EPSS (Exploit Prediction Scoring System)
Trend Analysis
EPSS (Exploit Prediction Scoring System)
Prevede la probabilità di sfruttamento basata su intelligence sulle minacce e sulle caratteristiche della vulnerabilità.
EPSS Score
0,0011
Percentile
0,3th
Updated
EPSS Score Trend (Last 79 Days)
502
Deserialization of Untrusted Data
DraftCommon Consequences
Security Scopes Affected:
Integrity
Availability
Other
Potential Impacts:
Modify Application Data
Unexpected State
Dos: Resource Consumption (Cpu)
Varies By Context
Applicable Platforms
Languages:
Java, JavaScript, PHP, Python, Ruby
Technologies:
AI/ML, ICS/OT, Not Technology-Specific
Application
Lmdeploy by Internlm
Version Range Affected
To
0.11.1
(exclusive)
CPE Identifier
View Detailed Analysis
cpe:2.3:a:internlm:lmdeploy:*:*:*:*:*:*:*:*
Common Platform Enumeration - Standardized vulnerability identification
https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh
https://github.com/InternLM/lmdeploy/commit/eb04b4281c5784a5cff5ea639c8f96b33b3…
https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh