Projects
Tools and applications I’m building to solve real security problems.
Gatekeeper
Client-side prompt injection scanner that analyzes LLM inputs against 21 detection rules across 7 attack categories. Terminal-style interface with severity-scored findings mapped to OWASP’s LLM Top 10. Links: GitHub Stack: Next.js, JavaScript, Vercel
Threat Pulse
Threat intelligence aggregator that consolidates IP, domain, and file hash lookups from AbuseIPDB, AlienVault OTX, and VirusTotal into a single SOC-style monitoring panel. Links: GitHub Stack: Next.js, Supabase, Vercel
CloudLint
Cloud security configuration analyzer that checks IAM policies, S3 configs, and security group rules against 15 CIS AWS Benchmark controls. IDE-style interface with line-level flagging and a VS Code-inspired problems panel. Links: GitHub Stack: Next.js, JavaScript, Vercel
Career Tracker
Personal dashboard for tracking certifications, training, and career milestones. Admin panel for logging entries, public dashboard for viewing progress at a glance with expiration countdowns and status tracking. Links: GitHub Stack: Next.js, Supabase, Vercel
Phishing Analysis Toolkit
Toolset for analyzing and dissecting phishing emails, extracting indicators of compromise, and automating initial triage workflows.
Links: GitHub Stack: Python, Email Parsing, IOC Extraction
Security Automation Playbooks
Collection of automated response playbooks for common security events, streamlining incident response and reducing manual investigation time.
Links: GitHub Stack: Python, Automation, Incident Response
Secret Scanner
CLI tool that catches leaked credentials in source code before they ship. 20+ detection rules, Shannon entropy analysis, git pre-commit hook, and SARIF output for GitHub Code Scanning.
Links: GitHub Stack: Python, Entropy Analysis, SARIF, DevSecOps
Secure Auth API
Full OAuth2-pattern REST API built from scratch with Python’s standard library. JWT signing, PBKDF2 password hashing, role-based access control, brute-force protection, and token rotation with no frameworks or pip installs.
Links: GitHub Stack: Python, JWT, PBKDF2, OAuth2, RBAC
AI Output Validator
Scans LLM responses for PII leakage, hallucinated claims, policy violations, and toxic content before they reach the end user. Uses the LLM-as-judge pattern for hallucination detection with offline regex checks as a baseline.
Links: GitHub Stack: Python, LLM-as-Judge, PII Detection
RAG Security Scanner
Tests Retrieval-Augmented Generation pipelines for indirect prompt injection, context poisoning, and data exfiltration. Includes a built-in TF-IDF retrieval engine so you can test without any external vector database.
Links: GitHub Stack: Python, RAG, TF-IDF, Prompt Injection
Prompt Injection Evaluator
Red-teams LLM system prompts by firing 40 injection payloads across 10 attack categories and scoring resistance. Canary-based detection with letter grades and weighted risk scoring for CI pipeline integration.
Links: GitHub Stack: Python, LLM Evaluation, Prompt Security