We Built An Agent That Broke All of Our Security Rules. Here's What We Learned.
// AI summary
Token learned that AI agents require dedicated identities, job-specific access, and separate traceability to defend against behaviors that break established security rules.
// from the source
We tell customers three things about securing AI agents: they need their own identities, access that fits the job they’re given, and traceability that’s separate from any human’s. That was true for us at Token as well. Then, we built an agent that broke all three by default. This helped us think through how such agents should be defended. When a browser agent acts inside a user’s authenticated