HackStack

Project Info

SnackHack

Devpost

Inspiration

Phishing and email spoofing remain the most common entry points for cyberattacks. We wanted to explore how easily users can fall for realistic but harmless emails—and how data-driven insights can strengthen awareness training and detection models.

What it does

Our project simulates controlled, lab-safe phishing campaigns using Wordware automation. It tracks delivery, opens, and clicks in a sanitized dashboard to measure human risk and gateway effectiveness. We also began developing a machine-learning and deep-learning pipeline to detect and classify malicious URLs, complementing the simulation with proactive defense research. How I built it We used Wordware for automation and telemetry visualization, Python + Flask for backend logging, and a mock SMTP setup to ensure all emails were contained within a sandboxed environment. Challenges I ran into Ensuring full ethical isolation—no real recipients or payloads. Managing asynchronous message tracking and accurate analytics visualization. Balancing detection accuracy and false-positive rates in URL classification. Time-boxing training runs on limited hardware during the hackathon. Accomplishments that I'm proud of End-to-end phishing simulation dashboard built safely within 24 hours. Actionable analytics showing how awareness and filters impact outcomes. Integration of an initial malicious-URL detection model for future defense modules. Clear demonstration of how offensive simulation data can inform defensive systems. What I learned Hands-on simulation, when done responsibly, provides the best understanding of real-world attack behavior. We learned to combine offensive-security insights with defensive ML research to build safer email ecosystems and better user education.

What's next

Integrate the ML URL detector into the simulation pipeline for real-time classification. Expand datasets and benchmark models for precision and recall. Open-source a training-mode simulator for organizations to test awareness safely. Develop an admin dashboard with real-time defense recommendations.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • HTMLIn code
  • JavaScriptIn code
  • ReactIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • PythonClaimed

6 of 7 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

23 KB

Source files

10

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars