Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Skyflow Adds Privacy Controls to AgentCore Gateway Tool Calls

AI summary

AWS Machine Learning Blog describes integrating Skyflow Detect with Amazon Bedrock AgentCore Gateway as a request and response interceptor for AI agent tool calls. The interceptor can de-identify outgoing data, restore permitted results, and replace documents with sanitized copies, while Skyflow is available through AWS Marketplace and the interceptor is open source on GitHub. String de-identification is generally available, but document handling through signed URLs uses Skyflow Detect v2 in preview.

In-depth insight

The integration applies privacy controls at a shared gateway point, potentially protecting sensitive data exchanged with MCP servers, SaaS APIs, document stores, web search, and models without modifying existing agents or tools.

In this post, we show how Skyflow and Amazon Bedrock AgentCore Gateway keep sensitive data out of the tools your AI agents call, and out of the model context those tools feed. We add Skyflow Detect to Amazon Bedrock AgentCore Gateway as a request and response interceptor. The Skyflow interceptor de-identifies data before it reaches a tool, restores it before the agent reads the result, and replaces documents with clean copies before the agent opens them. Your agents and tools don’t change.

Skyflow is available in AWS Marketplace, and the interceptor is open source on GitHub.

Agents act through tools, and tools move data

Agents have moved from answering questions to taking action, and they take action through tools: Model Context Protocol (MCP) servers, SaaS APIs, document stores, and web search. Every agent tool call is a data flow. Most enterprise controls cover what goes into and comes out of the model. Far fewer cover what an agent sends to its tools or what those tools send back.

That gap shows up in three ways:

  • Sensitive data leaves through tool arguments. The model writes the arguments from everything in its context, including details the tool doesn’t need. Ask an agent about a customer, and the customer’s name, account number, or email goes straight into a query to a third-party server. That server sits outside your AWS account and your compliance scope.
  • Sensitive data comes back in tool results. Scraped web pages, CRM records, and case notes land in the model’s context, memory, traces, and logs. This happens even when the task never needed them.
  • Documents bypass text inspection. Document tools such as Amazon Simple Storage Service (Amazon S3), Box, and Google Drive return a signed URL, not text. A filter that inspects strings sees a link and lets it through, and the agent then opens the original file.

#Skyflow#Amazon Bedrock AgentCore Gateway#Skyflow Detect#Skyflow Vault#AWS Marketplace#GitHub#AWS Lambda

Original · 12 min readRead the original
Group chat

No comments yet. Start the conversation.