Christopher Craig - Stacking the Deck

Agentic Workflows for Offensive Security Traditional offensive security is often a battle against the friction of manual reconnaissance, repetitive infrastructure setup, and the tedious translation of tool outputs into actionable reports. As Large Language Models evolve from static chat interfaces into autonomous agents, the role of the security professional is shifting from Manual Operator to Systems Architect. This session approaches offensive security through the lens of a deckbuilding card game. We will move beyond "vibe-based" prompting and explore how to build a production-grade Agentic Harness (i.e. the game board) that enforces deterministic rules, manages your "mana" (tokens), and anchors your agent to reality. Key Takeaways: The Setup (The Board): Building effective agentic harnesses to reduce false positives and get results. The Action (The Cards): Chaining your agent with automated script generation to transform fragile security discoveries into persistent, verifiable exploits. The Economy (The Mana): Strategies for maintaining low-cost operations by picking the right agent and "compiling" agentic reasoning into local tools and offloading repetitive tasks. Attendees will leave with a blueprint for building their own "Security Deck," enabling them to automate the grind, preserve high-level strategy, and execute complex engagements with the precision of a Systems Architect.