$ cat profile.txt
Hands-on exploit research at the intersection of cloud infrastructure & AI systems
$ cat mission.txt
Hands-on exploit research in controlled lab environments. Focused on LLM security, AI service misconfigurations, cloud infrastructure attack surfaces, and AI supply chain threats. All findings published with reproducible evidence.
$ ls focus/
A focused security audit of agentic AI orchestration frameworks — LangFlow, LangChain, CrewAI, AutoGen, and Haystack — with actively exploited CVEs, real breach costs, a self-hosted detection architecture, Terraform deployment, and a hands-on lab.
A deep-dive into the real cost of running a production API on AWS API Gateway + Lambda — including hidden fees across REST API calls, data transfer, caching, and CloudWatch logging — and a complete container-based alternative on Caddy + Docker that cuts your API bill by 96%.
A deep-dive into the real cost of running AWS NAT Gateway at scale — including the triple-dip billing across hourly, data processing, and data transfer fees — and a complete alternative architecture using fck-nat and VPC endpoints that cuts your bill by 95%.