Securing Agents with Open Standards — Bobby Tiernay and Kam Sween, Auth0
Jun 30, 2025 · 18:41
Bobby Tiernay and Kam Sween from Auth0 argue that production-grade AI agents must be secured using open identity standards like OAuth 2.1, token exchange, and SIBA to avoid the pitfalls of shared secrets, overly broad scopes, and lost audit trails. They explain that agents need a clear user identity to prevent the confused deputy problem, and that access should be scoped per user and per API with short-lived tokens from a vault. For retrieval-augmented generation, they advocate fine-grained authorization at the retrieval layer, not inside the LLM. Kam demonstrates a local trading agent that uses SIBA (client-initiated back-channel authentication) to request user approval via push notification without a browser, after the user authenticates once. The talk emphasizes that these patterns—async user consent, token exchange, and centralized credential management—are live today in standards and platforms like Auth0 and OpenFGA, enabling developers to build secure agents without reinventing the wheel.
