Here's What Agentic AI Can Do With Have I Been Pwned's APIs
This title could be clearer and more informative.Try out Clickbait Shieldfor free (5 uses left this month).
Troy Hunt demonstrates how agentic AI can interact with Have I Been Pwned's APIs via the Model Context Protocol (MCP). Using OpenClaw as an AI agent connected through a Telegram bot, he shows practical security use cases: identifying which employees appeared in a specific breach, analyzing stealer log data for corporate email addresses, discovering which external services employees are using with corporate credentials, and setting up background monitoring tasks that proactively alert on new breaches. The post also outlines HIBP's roadmap for deeper integration with mainstream AI tools like Claude and ChatGPT via OAuth, making breach data more accessible to non-technical users.
Sort: