I'm a full-stack developer and cybersecurity professional who bridges the gap between secure coding practices and threat analysis. Currently pursuing my Computer Science degree at MSU Denver [graduating Spring 2026], I build and audit robust applications while maintaining a security-first mindset.
🔬 Current Research: Conducting honors thesis on multi-agent LLM security vulnerabilities, developing an open-source testing framework for bili-core [AETHER] that enables systematic security evaluation of AI agent systems—addressing prompt injection, jailbreak attacks, checkpoint poisoning, and bias amplification.
- 💼 Working at The Sustainability Hub - NSF-funded program making Colorado's environmental data accessible through a specialized RAG chatbot
- 🤖 Developing Multi-Agent AI Security Testing Framework - Python framework for automated LLM security testing
- 📚 Researching Multi-agent AI Security, Prompt Injection Attacks, LLM Vulnerabilities
- 🌱 Learning Web Application Security & Advanced Penetration Testing in preparation for taking Hack the Box's Certified Penetration Testing Specialist applied exam
- 🏆 Cybersecurity Competitions: MWCC 2023/2024, RMCCDC 2025
- 🔭 Later: Building Vulnerable Web Application - Flask app with intentional security flaws + secure refactor
Developing an extensible security testing framework for early-stage multi-agent AI systems:
Research Focus:
- 🎯 Checkpoint Architecture Vulnerabilities - Attack vectors exploiting state persistence
- 🔄 Cross-Model Attack Persistence - Security vulnerabilities across different LLM providers
- 🧠 Memory Management Security - Resilience against injection and poisoning attacks
- 📋 Security Framework Development - Guidelines for production multi-agent systems
Key Contributions:
- Open-source multi-agent testing framework for bili-core
- Systematic vulnerability analysis across five attack dimensions
- Empirical security evaluation methodology
- Organizational security guidelines for AI deployment
Python framework using multiple LLM agents for automated security testing
- Multiple agent roles: attacker, defender, analyzer
- Automated security test generation and analysis
- Integration with security tools and APIs
- Direct application of honors thesis research
- Tech Stack: Python, LangChain, OpenAI/Anthropic APIs, pytest
Flask application demonstrating common vulnerabilities and secure remediation
- Intentional vulnerabilities: SQL injection, XSS, insecure file upload, weak sessions
- Comprehensive security documentation for each vulnerability
- Proof-of-concept exploits with code examples
- Secure refactored version with fixes
- Before/after security comparison report
- Tech Stack: Flask, Python, SQLAlchemy, PostgreSQL
Comprehensive security assessment of intentionally vulnerable application
- Full PTES/OWASP methodology implementation
- Executive summary and technical findings
- CVSS severity ratings and risk analysis
- Proof-of-concept exploit demonstrations
- Detailed remediation recommendations
- Target: DVWA/WebGoat/OWASP Juice Shop
- Entry-Level Penetration Testing positions
- Application Security positions
- Software Development roles with security focus
- Cybersecurity Engineering positions
- Cybersecurity Analyst positions
- Security Research & Development opportunities
- AI/ML Security Research opportunities
- DevSecOps opportunities
