InternLM LMDeploy
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
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.
First public PoC
None yetno public PoC found
Public PoCs00 on GitHub
CVSS8.8high · scored by CNA · CWE-400
CISA KEV
Not listednot known exploited
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
InternLM lmdeploy
- >= 0.12.1, < 0.12.3
Fixed in 0.12.3
Mitigation
Upgrade lmdeploy to 0.12.3 or later.
References
- Vendor advisory github.com/InternLM/lmdeploy/security/advisori…
- Release notes github.com/InternLM/lmdeploy/releases/tag/v0.1…
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.No PoC repositories found yet.