JayanthC6/online-harassment-detection ? reverse-engineered prompt

Build me a full stack cyber safety app called ShieldAI for detecting online harassment, scams, threats, and phishing.

I want a public facing tool where someone can paste text, upload a chat export, screenshot, PDF, or audio file, and get back a risk score, a simple explanation, and clear safety advice. It should also have an admin dashboard for moderators with a queue of reports, trend charts, incident details, and a way to track repeat offenders over time.

Please include a chatbot that can talk in two modes, one for victims who need help and one for analysts who want investigation support. Add a Chrome extension that can scan visible messages on the page and show color coded risk badges next to suspicious content.

Keep the UI clean and modern, make it feel production ready, and use a Python backend with a React frontend. If you need current library details, look them up online before wiring things up.