Description
LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to execute arbitrary Python code by supplying a malicious model path in the Chat or Training interfaces. The application passes user-supplied model path input unvalidated into AutoTokenizer.from_pretrained() and AutoModel.from_pretrained() with a hardcoded trust_remote_code=True parameter, causing the Hugging Face transformers library to fetch and execute arbitrary code from a remote or local model repository with the privileges of the server process.
Metrics
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| hiyouga | LlamaFactory | <= 0.9.5 |
References
- https://gist.github.com/henrrrychau/08d76ec672f42136bbc1449c4f2973f8Exploit, Mitigation, Third Party Advisory
- https://www.vulncheck.com/advisories/llama-factory-remote-code-execution-via-webui-model-pathThird Party Advisory
Timeline
- Published
- Jun 30, 2026
- Last modified
- Jul 14, 2026
- NVD status
- Analyzed