Benchmarking Agent Safety in Browsers

As AI agents are increasingly given access to the live web to perform tasks (e.g., "book a flight," "summarize this news site"), they face a new class of security threats. Unlike chat interfaces where input is clearly defined, the web is a messy, untrusted environment. This lesson explores Indirect Prompt Injection in the browser and how benchmarks like BrowseSafe are establishing standards for agent defense.