ScamShield

Inspiration

I wanted to make the internet safer for everyone. Phishing and scam websites are everywhere, and most users don’t have an easy way to check if a URL is safe. My goal was a simple, one-click tool anyone can use.

What it does

ScamShield lets users paste a URL and instantly see: Risk score & level (Low, Medium, High) Reasons why a URL is suspicious AI-style report explaining the potential threat Even if the Gemini AI fails, a fallback report is shown so users always get feedback.

How we built it

Backend: Python + FastAPI handles scanning and API requests. URL analysis: Heuristics check URL length, subdomains, suspicious keywords, shorteners, IP-based domains, etc. AI reports: Gemini API generates human-readable summaries. Fallback logic ensures results even if the API is down. Frontend: HTML/CSS/JS for a clean, responsive interface.

Challenges we ran into

Gemini API sometimes fails → solved with a fallback report. Explaining technical URL risks in simple language. Making frontend and backend communicate smoothly (CORS, fetch requests).

Accomplishments that we're proud of

Built a fully working URL scanner combining heuristics + AI insights. Designed resilient fallback logic so users always see results. Created a simple, mobile-friendly UI that anyone can use.

What we learned

How to integrate AI APIs and handle errors. How to design heuristic-based URL security checks. The importance of user-friendly design for non-technical users.

What's next for ScamShield

Deploy as a live web app. Add a browser extension for one-click scanning. Track URL scan history for users.

Built With

• css
• fastapi
• html
• javascript
• python