LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
InternLM lmdeploy
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| lmdeploy PyPI |
|
|
Original 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.
From the CVE record · GitHub_M