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)
EPSS: 0.006 (47.2th percentile) — read the EPSS interpretation.
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.
Affected products
- Hiyouga Llama-factory
- Hiyouga Llamafactory — versions 0
Weakness classification (CWE)
Public proof-of-concept exploits
References
- disclosure@vulncheck.com (Exploit, technical-description, Third Party Advisory, exploit, Mitigation)
- disclosure@vulncheck.com (Third Party Advisory, third-party-advisory)
Frequently asked questions
- What is CVE-2026-58116?
- CVE-2026-58116 is a critical-severity vulnerability in Hiyouga Llama-Factory, classified under Code Injection. CVSS score: 9.8/10. Published 2026-06-30.
- How severe is CVE-2026-58116?
- Critical severity. CVSS v3 base score is 9.8 out of 10.
- Is CVE-2026-58116 known to be exploited?
- 1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.