proomt

Search

Search posts, papers, and topics

All posts

Auth017 min readintermediate

Building Secure AI Agents with Microsoft Agent Framework and Auth0: Human-in-the-Loop Approval

Read on auth0.com

Summary

This article demonstrates how to implement human-in-the-loop approval for an AI expense agent using Auth0's Client-Initiated Backchannel Authentication (CIBA). It enables secure, out-of-band manager approval via push notifications with specific binding messages, preventing the LLM from handling sensitive credentials.

  • CIBA allows backend apps to initiate out-of-band authentication, pushing approval requests to a user's enrolled device.
  • Binding messages are critical for CIBA security, providing clear context for the user's approval decision.
  • The AI agent polls Auth0's /token endpoint to retrieve the manager's approval or denial.
  • CIBA requires confidential clients and specific Auth0 configurations, including API permissions and Guardian push notifications.

Engineers building AI agents that perform sensitive, irreversible actions will find this valuable for securely integrating human oversight and approval workflows.

7/10
api designsecurityai agentsauthenticationauth0ciba

Related reading

  1. Auth0 Agent Gateway: The Identity Control Plane for Customer-Facing AI

    Auth0 Agent Gateway is a beta CIAM control plane that lets SaaS teams govern product‑native, customer‑facing AI agents. It adds organization‑aware identity, token‑exchange‑based credential delegation, real‑time policy checks, audit logging and a kill‑switch, aiming to prevent cross‑tenant data leaks and unauthorized tool use.

    Auth0auth0.com6 min

  2. APort Vault: Benchmarking AI Agent Payment Authorization with the Open Agent Passport

    APort Vault is a benchmark that replays 4,371 human‑written attacks against a live payment‑handling AI agent across 14 models and multiple policy configurations, generating 225,964 evaluations. Adding the Open Agent Passport pre‑action check eliminated all unauthorized transfers in the test, showing a per‑session breach upper bound of 0.38%.

    Hugging Face Daily Papersarxiv.org2 minpaper

  3. Changing the game: How Google uses agentic AI to secure hundreds of millions of lines of code

    Google’s AI & Infrastructure team built an agentic pipeline (Mantis) that runs pre‑submit AI‑driven scans on every code check‑in, validates findings with a fast triage agent (AST + call‑graph analysis) achieving >92% precision in <1 min, then auto‑generates fixes via a bug‑fix agent. Localized threat models and a two‑step scan cut false‑positives to ~3% and prevent hundreds of vulnerabilities eac…

    Google Cloud Bloggoogle.com4 min

  4. Podcast: Securing AI Agents: Identity, Authorization, and the DPACT Framework

    This podcast discusses the critical challenges of identity, authorization, and security for AI agents. It introduces the DPACT framework (Delegation, Policy, Auditability, Context, Time) as a blueprint for building responsible agentic systems with bounded, delegated authority, moving beyond simple token-based access.

    InfoQinfoq.com29 mintalk

  5. Building Sentry's Laravel AI Integration

    Sentry added zero‑config Agent Tracing for Laravel AI agents. The integration hooks into Laravel AI events and HTTP request events to create Chat spans for each LLM call, matching requests by provider URL prefix. Updating to sentry‑laravel 4.27 automatically instruments agents without any user code changes.

    Sentrysentry.io4 min