A LinkedIn-based LLM jailbreak game where users attempt to bypass Gandalf's system prompt through comments on a LinkedIn post.
Inspired from the great Gandalf Lakera
This project creates an interactive game that:
- Monitors a specific LinkedIn post for comments
- Uses an LLM (playing as Gandalf) to respond to user attempts
- Allows each user only one attempt to bypass the system prompt
- Automatically responds to new comments
- Tracks user attempts to prevent multiple tries
- Clone the repository:
git clone https://github.com/lucebert/gandalf-linkedin.git
cd gandalf-linkedin- Install dependencies using Poetry:
poetry install- Set up environment variables:
cp .env.example .envRun the application:
poetry run python -m gandalf_linkedin.mainpoetry run pytestThis project is released into the public domain under The Unlicense. See the LICENSE file for details.