SyndiGuard

Inspiration

When I was 11, I saw my best friend getting scammed by a random person through Roblox, i didn't know coding at that time, but I do now, and when I remembered him, I got the idea of what is was going to build .

What it does

It stores scam reports, analyzes them and helps you analyze if the message was a scam. It also links scams and decompresses or resolves unwanted redirects in a suspicious sites.

How we built it

We built it using VS Code, Thinkpads, Windows 11, ChatGPT(for research and complex debugging what we couldn't do) and pure determination

Challenges we ran into

We ran into a problem in the backend among others, but i feel that this took the most time. In this problem, the scam linker/analyzer would classify death threats as 10/100 danger score, which was an extremely underwhelming result. This bug took 3 rewrites to the main files in the codebase and causing us to lose a lot of time.

Accomplishments that we're proud of

Me, and my teammate are proud that we used our coding skills for the first time without full reliance on AI, as before this we would always use AI to do most of the work, whereas this time we used our skills without using AI for everything, we also had our first major "aha" moment when our code was working fully functional for the first time.

What we learned

We learned a lot of things from this, first of all, this was me and my teammates first non-AI hackathon so we did'nt use AI except for a few tasks like some javascript errors and highly complex debugging in some cases that was way above our heads.

What's next for SyndiGuard

We hope that we would fix bugs, add more features and deploy this as a fully functional web app!

Built With

• css3
• html5
• javascript
• llama.cpp
• python
• urlscan.io-api