8.8High

CVE-2026-33625LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading

InternLM lmdeploy Published: (2 months ago)

Description

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.

Weakness (CWE): CWE-400

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
InternLM lmdeploy >= 0.12.1, < 0.12.3

References and patches