LLaMA-Factory 0.9.5 Remote Code Execution via WebUI Model Path
48Vexday Risk Score
No sign of exploitation. It has a public proof of concept.
ssvc Attendcvss 9.3epss 0.6%
from disclosure to weapon2 days
Published on NVDJun 30
1st PoC+2d
exploitation probability
0.6%top 52% of all CVEs
observed exploitation
nono source reports it
2 public exploit(s)
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:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Affected products
hiyouga · LlamaFactorypublic PoCs found — 2
githubgithub.com/Hunt-Benito/llama-factory-webui-rce-cve-2026-58116-trust-remote-code-model-path-injection★ 0cve_referencegist.github.com/henrrrychau/08d76ec672f42136bbc1449c4f2973f8unverified⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.