LASCon - Hidden Risks of Integrating AI

This talk explores the hidden risks in apps leveraging modern AI systems—especially those using large language models (LLMs) and retrieval-augmented generation (RAG) workflows and demonstrates how sensitive data can be extracted through real-world attacks. It touchpoints back to OWASP principles and the LLM Top 10 while demonstrating attacks for extracting data and for abusing MCP servers and agents.