CVE-2026-33625
Published:September 18, 2026
Updated:October 09, 2026
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in "lmdeploy/pytorch/config.py" line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model with a crafted "quantization_config.quant_dtype" value. When a user loads the model with lmdeploy, the "quant_dtype" is passed to "eval(f'torch.{quant_dtype}')" without any validation. Version 0.12.3 contains a patch.
Affected Packages
https://github.com/InternLM/lmdeploy.git (GITHUB):
Affected version(s) >=v0.7.0 <v0.12.3Fix Suggestion:
Update to version v0.12.3lmdeploy (PYTHON):
Affected version(s) >=0.7.0 <0.12.3Fix Suggestion:
Update to version 0.12.3lmdeploy (PYTHON):
Affected version(s) >=0.12.1 <0.12.3Fix Suggestion:
Update to version 0.12.3Related Resources (7)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.7
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
PASSIVE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
HIGH
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
8.8
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
REQUIRED
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH
Weakness Type (CWE)
Uncontrolled Resource Consumption
EPSS
Base Score:
0.44