Vulnerability 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.
CVSS Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Hiyouga | Llama-Factory | <= 0.9.5 |
Related Weaknesses (CWE)
References
- https://gist.github.com/henrrrychau/08d76ec672f42136bbc1449c4f2973f8ExploitMitigationThird Party Advisory
- https://www.vulncheck.com/advisories/llama-factory-remote-code-execution-via-webThird Party Advisory
FAQ
What is CVE-2026-58116?
CVE-2026-58116 is a vulnerability with a CVSS score of 9.8 (CRITICAL). 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 T...
How severe is CVE-2026-58116?
CVE-2026-58116 has been rated CRITICAL with a CVSS base score of 9.8/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-58116?
Check the references section above for vendor advisories and patch information. Affected products include: Hiyouga Llama-Factory.