CVE-2026-33625 LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
HighCVSS 8.8
EPSS 0.44%
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: no · technical impact: total
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.
Upgrade path
2 packages: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| pypi lmdeploy(PyPI) | = 0.12.1; = 0.12.2; >= 0.12.1, < 0.12.3 | 0.12.3 | Fixed |
| InternLM lmdeploy | = >= 0.12.1, < 0.12.3 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| pypi lmdeploy(PyPI) | >= 0.12.1, < 0.12.3 | 0.12.3 |
| pypi lmdeploy(PyPI) | = 0.12.1 | No fix listed |
| pypi lmdeploy(PyPI) | = 0.12.2 | No fix listed |
| InternLM lmdeploy | = >= 0.12.1, < 0.12.3 | No fix listed |
References
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr exploit vendor-advisory
- github.com product
- https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3
- pypi.org product
- github.com vendor-advisory
- nvd.nist.gov vendor-advisory
- ENISA EUVD EUVD-2026-83202 third-party-advisory