AI Agent Security Submit an agent

Securing AI agents, in practice.

Field notes on how agents get attacked through what they read and what they can call, and the controls that hold up in production.

How AI Agents Really Work Under the Hood, Frame by Frame

How an AI agent works under the hood: a Python loop, an MCP server, an LLM and 25 Splunk events read frame by frame. Code snippets and a lab to rebuild it.

→