Implement Safety Measures for Dangerous Commands in `AiShell`

code-yeongyu / AiShell

AiShell: A Natural Language Shell like GitHub Copilot X, Powered by ChatGPT

MIT License

151 stars 14 forks source link

Implement Safety Measures for Dangerous Commands in `AiShell` #2

Closed code-yeongyu closed 1 year ago

code-yeongyu commented 1 year ago

It would be great if the system could implement some safety measures for commands that could potentially cause harm, such as:

handling git
removing files permanently

The idea is that, before executing any dangerous command, AiShell could ask the user for confirmation. This way, accidental execution of harmful commands can be prevented.

code-yeongyu commented 1 year ago

considering now to ask everytime Y/N prompt to execute the command or not, because it's much easier way to implement.