CVE-2026-33625
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
- State
- Published
- Severity
- 8.8 High
- Published
- Sep 18, 2026
- Updated
- Sep 22, 2026
- Reserved
- Mar 23, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 8.8 High | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | GitHub_M |
Weaknesses
- CWE-400 Uncontrolled Resource Consumption
Affected Products
| Product | Versions |
|---|---|
lmdeployInternLM |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.