Static

Unsloth Studio Flaw Turns Routine Model Inspection Into Code Execution

First reported by Dark Reading ·

The signal ●○○○ Brief pending · reported by Dark Reading, the single source so far
What happened

A patched Unsloth Studio vulnerability allows malicious AI models to execute arbitrary Python code during inspection, via the trust_remote_code setting.

Source description shown. AI brief pending.

Unsloth