You’ve seen the tweets about vibe-coded apps getting hacked over silly mistakes — but what can we actually do about it? AI coding agents are amplifiers: they ship faster, but they also ship insecure code, and asking them to “make it secure” rarely works.

Security This talk shows a better approach: shift the focus from chasing specific attacks to teaching solid defensive coding principles. We’ll build security knowledge directly into the agent — using skills, hooks, and standards — so it looks up the right guidance, plans for it, and reviews its own work. You’ll leave knowing how to make your agent produce secure code far more often, by default.