CVE-2026-58116
LLaMA-Factory 0.9.5 Remote Code Execution via WebUI Model Path
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.
INFO
Published Date :
June 30, 2026, 12:54 p.m.
Last Modified :
June 30, 2026, 12:54 p.m.
Remotely Exploit :
Yes !
Source :
VulnCheck
Affected Products
The following products are affected by CVE-2026-58116
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | CRITICAL | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 3.1 | CRITICAL | [email protected] | ||||
| CVSS 4.0 | CRITICAL | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 4.0 | CRITICAL | [email protected] |
Solution
- Update LLaMA-Factory to version 0.9.5 or later.
- Review and sanitize all user-supplied model paths.
- Disable trust_remote_code parameter when possible.
- Restrict WebUI access to authorized users.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-58116 vulnerability anywhere in the article.