TraceTree is a tool I've been building that scans files for malicious behavior before you run them. It combines radare2 disassembly, YARA rule matching, and a small ML pipeline to flag risky files, then shows the verdict in a dashboard instead of leaving you to read raw logs.
I just wrapped up OpenAI Build Week with another round on it. It's not a project I built for hackathons, it's something I keep working on for its own sake, but I bring it along whenever a hackathon allows existing projects. It's become my favorite way to learn a new AI stack without throwing the work away after.
This round the stack was Codex with GPT-5.6, and the fix that mattered most was a quiet one. The backend was never emitting a "malicious" verdict in certain cases, so genuinely dangerous scans were showing up as a yellow caution instead of red danger. Codex helped me trace that bug across the orchestrator, the server, and the frontend before I nailed down the fix.
The real lesson every hackathon reteaches me is what to hand an agent and what needs my own judgment. A wide open scan burns credits with barely any signal. A narrow, scoped ask gets you something you can actually verify.
TraceTree keeps growing one hackathon at a time, and I keep learning something different about working with these tools each round.
Repo Link: TraceTree