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

September 18, 2026

lmdeploy <= latest contains 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.

References

github.com/InternLM/lmdeploy/releases/tag/v0.12.3
github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr
github.com/advisories/GHSA-3hmm-rh5q-gwwr
nvd.nist.gov/vuln/detail/CVE-2026-33625

Code Behaviors & Features

Detect and mitigate CVE-2026-33625 with GitLab Dependency Scanning

Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Dependency Scanning using SBOM also detects vulnerabilities from proprietary advisories that this site does not include. Learn more about Dependency Scanning using SBOM →