LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading (InternLM lmdeploy)
At a glance
- Source
- NVD
- EPSS
- EPSS 0.44 % · percentile 38 ()
- State
- PUBLISHED
- Published
- Updated
- Assigner
- GitHub_M
- NVD status
- Deferred
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.
Weaknesses (CWE)
- CWE-400 — Uncontrolled Resource Consumption
References
Scores
| Version | Score | Vector | Scored by |
|---|---|---|---|
| CVSS 3.1 | HIGH 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | GitHub_M |
| CVSS 3.1 | HIGH 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | NVD · security-advisories@github.com (Secondary) |
Advisories
- GHSA-3hmm-rh5q-gwwr — LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
- PYSEC-2026-4078 — LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
European references
- ENISA EUVD · EUVD-2026-83202
- GCVE · GCVE-0-2026-33625
Affected products
| Product | Versions |
|---|---|
| InternLM · lmdeploy | affected >= 0.12.1, < 0.12.3 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |