A AegiFlow
HIGHCVSS 8.8EPSS 0.2%

CVE-2026-33625

CVE-2026-33625 updated by NVD

Published
2026-09-18
Modified
2026-09-20
EPSS percentile
16%
Sources
github-advisory, nvd

Summary

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

EcosystemPackageAffected versionsFixed versions
PyPIlmdeploy0.12.3

Remediation: Upgrade to 0.12.3 or later.

References

Includes data from the GitHub Advisory Database, licensed under CC-BY 4.0.

Includes data from the National Vulnerability Database (NIST). NVD data is in the public domain; this page is not endorsed by NIST.

CVE® is a registered trademark of The MITRE Corporation. CVE content reproduced under the CVE Terms of Use; copyright designation © MITRE.

EPSS scores provided by the FIRST.org Exploit Prediction Scoring System.