FR
live
High CVSS 8.8

CVE-2026-58116

Hiyouga Llama-factory

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.

What this means

Exposure
Exploitable remotely over the network, with an ordinary user account and with no action from the victim.
Impact
An attacker can read sensitive data, modify or destroy data and take the service offline.
Weakness
The application interprets attacker-supplied code, which then runs with its privileges.
Likelihood
Its EPSS score stays low: nothing points to imminent exploitation, which is no reason to leave it unpatched.

What to doFold into the next patch cycle.

Read automatically from the CVSS vector, the weakness type (CWE) and the EPSS score. The technical description above remains the one published by NIST.

Published
30 June 2026
CVSS
8.8 (v3.1) CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
EPSS
0.64% probability of exploitation within 30 days · above 47% of all CVEs
Weakness
CWE-94CWE-829
Sources
nvd
References

Type at least two characters.

navigate open esc dismiss