What’s Vulnerable › Vulnerabilities

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

• Severity: high (CVSS 8.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.4% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-09-18 · updated 2026-09-24
• Weakness: CWE-400

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.

Affected products

• InternLM lmdeploy: from 0.12.1, < 0.12.3

References

• https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3
• https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr
• https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr

Get alerted when CVE-2026-33625 or the next vulnerability affects your stack