CVE-2026-33625PYSEC-2026-4078GHSA-3HMM-RH5Q-GWWR
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 0.12.3
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
CISA's decision points: whether it is exploited, whether attacks can be automated, and how much control an attacker gets. Assessed (SSVC 2.0.3).What do these mean? →
- Exploitation: poc
- Automatable: no
- Technical impact: total
Summary
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.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: poc · Automatable: no · Technical impact: total
- Record last updated
Affected versions
- InternLM lmdeploy
From 0.12.1 · fixed in 0.12.3
- lmdeployPyPI
From 0.12.1 · fixed in 0.12.3