8.8High

CVE-2026-33625

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.

What this means for your business

  • An attacker can use it remotely, over a network, without a login, but only after tricking someone into an action such as opening a file or a link.

What to do

  1. 1Ask your IT team or provider whether any of your systems use the affected product.
  2. 2If you do, follow the vendor's guidance. No patch reference has been published yet.

Not sure if your company is exposed?

Fastnexa’s certified penetration testers can check whether attackers could use this flaw, or others like it, against your websites, apps and network. The full test is free for our first 10 founding clients until 31 December 2026.

Scoring

CVSS
8.8 (v3.1)
Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Weakness
CWE-400
Assigned by
security-advisories@github.com

Dates

Published
2026-09-18
Last modified
2026-09-18
Sources
NVD

References