Module 1: AI in Pentesting – Foundations
•Role of AI in modern pentesting
•Where AI helps vs where it fails
•Threat model: hallucinations, bias, OPSEC
•Legal & ethical boundaries
•Human-in-the-loop mindset
Module 2: Local LLMs for Security Work
•Why local LLMs (privacy, OPSEC, cost)
•Local LLM runtimes (Ollama, OpenWebUI, LM Studio, etc.)
•Model selection for security & code
•Prompting techniques for pentesters
•Validating AI outputs
Module 3: AI-Assisted Recon Workflows
•Recon pipeline with AI integration
•Passive recon analysis with LLMs
•Active recon output summarization
•JavaScript & API surface analysis
•Prioritizing attack surface with AI
Module 4: MCP Servers for Pentesting
•What MCP is and why it matters
•MCP architecture & components
•Tool orchestration using MCP
•Safe automation use cases
•AI + MCP workflow patterns
Module 5: Hands-On Lab – End-to-End Recon
•Reviewing scoped target data
•AI-driven recon analysis
•MCP-based tool chaining
•Finding correlations & anomalies
•Human validation of AI findings
