LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization
InternLM lmdeploy
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| lmdeploy PyPI |
|
|
Original description
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trust_remote_code=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no publicly available patches.
From the CVE record · GitHub_M