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

Best practiceRunning agents

Lock down every channel that can carry data out

OWASP ASI01OWASP LLM02OWASP LLM05

EchoLeak, ShadowLeak, CamoLeak and AgentFlayer all leaked data through an image URL, a link or a fetch the agent was allowed to make. Rendering and fetching are exits, even when the agent has no "send" tool.

What to do

  1. Do not render markdown images or auto-fetch links from model output; if you must, proxy through an allow-list of hosts.
  2. Give network tools a host allow-list per agent and deny by default.
  3. Strip secrets and personal data from tool results before they reach a model that can reach the internet.
  4. Alert on outbound requests to hosts an agent has never used before.

Sources

Check your own AI plan against the practices: Plan check