Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

Best practiceRunning agents

Never combine private data, untrusted content and an exit in one agent

OWASP ASI01OWASP ASI02OWASP LLM02

Simon Willison's "lethal trifecta": an agent that can read your private data, is exposed to untrusted content and can send data out (a web request, an email, a markdown image) can be made to leak that data. Remove one leg and the exfiltration path closes.

What to do

  1. List each agent's three legs: what private data it can reach, what untrusted content it reads, and every channel that can carry data out.
  2. Cut one leg per agent. A research agent that reads the web gets no private data; an agent over private data gets an egress allow-list and no free-form URLs.
  3. Split risky jobs into two agents with a narrow, validated hand-off instead of one agent that does everything.
  4. Review new connectors and MCP servers for which leg they add before enabling them.

Sources

Check your own AI plan against the practices: Plan check