CVE-2026-33625
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
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.
INFO
Published Date :
Sept. 18, 2026, 6:17 p.m.
Last Modified :
Sept. 18, 2026, 6:17 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | MITRE-CVE | ||||
| CVSS 3.1 | HIGH | [email protected] |
Solution
- Update LMDeploy to version 0.12.3 or later.
- Avoid loading untrusted models.
- Review model quantization configurations.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-33625.
| URL | Resource |
|---|---|
| https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3 | |
| https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-33625 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-33625
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-33625 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-33625 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Sep. 18, 2026
Action Type Old Value New Value Added 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. Added CVSS V3.1 AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CWE CWE-400 Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/33xxx/CVE-2026-33625.json">CVE-2026-33625</a> Added Reference https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3 Added Reference https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr