██████ ██ ██ ██████ ██████ ██ ███████ ███████
██ ██ ██ ██ ██ ██ ██ ██ ██ ██
██ ██ ██ ██ ██ ██ ██ ██ █████ ███████
██ ██ ██ ██ ██ ██ ██ ██ ██ ██
██████ ██████ ██████ ██████ ███████ ███████ ███████
Cuddles is an infrastructure project focused on Large Language Models (LLMs) and automated security testing.
- Task: Request information from the user.
- Action: Save the information to a dedicated ChromaDB instance for later access by an LLM.
- Task: Run basic active scans on provided targets.
- Action: Gather information (e.g., open ports, detected services) and add it to the ChromaDB database to be accessed by later stages.
- Task: Utilize the information from stages one and two.
- Action: Create an automated attack plan using an agent group chat.
- Task: XXXXXXXX
- Action: XXXXXXXX
- exmodder Dynamic exploit modification based on NMAP scan results
- cuddlesgroupchat/EXEC NMAP scans fed into an autogen groupchat with execution capability
We welcome contributions! Here's how you can help:
- Fork the repository
- Create a new branch (
git checkout -b feature-branch
) - Make your changes
- Commit your changes (
git commit -m 'Add some feature'
) - Push to the branch (
git push origin feature-branch
) - Open a pull request
For more information or any queries, feel free to reach out:
- Email: [email protected]
- GitHub Issues: Cuddles Issues
This project is licensed under the MIT License - see the LICENSE file for details.
- Thanks to colleages and friends at the Multiverse School.
- Special thanks to the open-source community.