CVE-2026-33625LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
Updated under an hour ago ()
Does this affect you?
It affects InternLM lmdeploy. Add what you run to find out whether that includes you.
No exploitation reported and no EPSS estimate yet.
Do this next
Free account, 1 product
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.
- CVSS
- 8.8 HIGH (v3.1, CNA)CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Weakness (CWE)
- CWE-400
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- GitHub_M
- NVD analysis
- Deferred
- Record last updated
- Sep 22, 2026
- First seen by InfoSec Signals
- Oct 9, 2026
Affected products
InternLM lmdeploy internlm:lmdeploy (from the name) | from 0.12.1, < 0.12.3 | CNA record |
References
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwrx-refsource-confirm
- https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3x-refsource-misc
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.