RCE in Hiyouga Llama-Factory
CVE-2026-58116
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.
Vulnerability class: RCE (Remote Code Execution)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.009, 60.3th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Hiyouga Llama-Factory
- Hiyouga Llamafactory — versions 0
Weakness classification (CWE)
Public exploits and proof-of-concept code
1 public repository with exploit or proof-of-concept code for this CVE:
- Hunt-Benito/llama-factory-webui-rce-cve-2026-58116-trust-remote-code-model-path-injection (last pushed 2026-07-02)
References
- Researcher Disclosure (Exploit, technical-description, exploit, Third Party Advisory, Mitigation)
- www.vulncheck.com/advisories/llama-factory-remote-code-execution-via-webui-mode… (Third Party Advisory, third-party-advisory)
This CVE has public exploit evidence. See the latest CVEs with public exploits.