CVE-2026-33625

8.8 HIGHpublic exploit available

Published 2026-09-18 · Updated 2026-09-24

AI risk analysis

Summary: The flaw allows an attacker to execute arbitrary Python code by crafting a specific `quantization_config.quant_dtype` value, leading to remote code execution.
Exploitability: Exploitation is relatively straightforward given the attacker can control the `quantization_config.quant_dtype` value. The precondition is the user must load the malicious model.
Blast radius: If exploited, the impact could be severe, potentially allowing full control over the system hosting the `lmdeploy` service.
Detection: No reliable host or network indicator is derivable from the published description.
Prioritized remediation: Upgrade to version 0.12.3 or later.

rcepython-code-executionremote-code-executionlmdploysecurity-vulnerability

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD 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.

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Weaknesses

CWE-400

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.