1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl
Chi tiết nguồn
<p>In this post, we show how <a href="https://www.skyflow.com/" target="_blank" rel="noopener">Skyflow</a> and Amazon Bedrock <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway.html" target="_blank" rel="noopener">AgentCore Gateway</a> 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 <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-interceptors.html" target="_blank" rel="noopener">interceptor</a>. 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.</p> <p>Skyflow is available in AWS Marketplace, and the interceptor is open source on GitHub.</p> <h2 id="agents-act-through-tools-and-tools-move-data">Agents act through tools, and tools move data</h2> <p>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.</p> <p>That gap shows up in three ways:</p> <ul> <li><strong>Sensitive data leaves through tool arguments.</strong> 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.</li> <li><strong>Sensitive data comes back in tool results.</strong> 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.</li> <li><strong>Documents bypass text inspection.</strong> 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.</li> </ul> <p>Patching each agent doesn’t scale across teams and frameworks, and it can’t reach third-party tools. The controls need to sit where every tool call passes, so authorization, content safety, and data protection apply the same way to every agent and tool.</p> <p>AgentCore Gateway is that place. It fronts every tool an agent uses, whatever framework or model the agent runs on. It does more than route that traffic. With AgentCore Gateway interceptors, you can run your own code, as an AWS Lambda function, on every call that passes through it. A request interceptor sees each call before it reaches a tool, and a response interceptor sees each result before it reaches the agent. Either one can inspect the payload, rewrite it, or block the call. That makes the gateway a natural place to add data protection alongside Policy and Guardrails. This single control, attached once, covers every agent and every tool behind the gateway, without any change to agent or tool code.</p> <h3 id="example-a-dispute-resolution-agent-at-a-large-european-bank">Example: A dispute-resolution agent at a large European bank</h3> <p>Consider a large European bank with retail and corporate banking operations and strict data-residency obligations. Its operations teams are adopting agents to investigate card disputes.</p> <p>An analyst asks the agent to look into a disputed transaction. The agent searches the web for the merchant, then pulls the dispute case note from Amazon S3 to summarize it. Without protection, three things happen:</p> <ul> <li>The model builds the search query from everything in context. The search provider receives ‘Mateo Jackson dispute AnyCompany Electronics London’. That’s the customer’s name, sent to a third party, for a search that only needed the merchant.</li> <li>Scraped merchant pages bring unrelated personal data into the model’s context.</li> <li>The agent reads the original case note, with the customer’s full name, email, phone number, and card details.</li> </ul> <p>With the Skyflow interceptor on the gateway, the same workflow plays out differently:</p> <ul> <li>The search provider receives ‘[NAME_AJbrIud] dispute AnyCompany Electronics London’, where [NAME_AJbrIud] is a reversible vault token. The merchant results come back the same, the provider never learns who the customer is, and the analyst still sees the real name in the agent’s answer.</li> <li>Web content reaches the model already de-identified.</li> <li>The agent only ever receives a link to a de-identified copy of the case note.</li> </ul> <h2 id="solution-overview">Solution overview</h2> <p>The Skyflow interceptor is a single AWS Lambda function attached to both of the AgentCore Gateway interception points:</p> <ul> <li><code>REQUEST</code> runs before the gateway calls a tool.</li> <li><code>RESPONSE</code> runs after the tool answers and before the agent sees the result.</li> </ul> <p>At each point, it calls Skyflow Detect to find sensitive entities such as names, email addresses, phone numbers, government IDs, card numbers, dates of birth, and locations. It replaces them with tokens, or restores the originals. Skyflow Vault stores the original values so authorized systems can reverse the tokens.</p> <p>The Skyflow gateway configuration decides, for each tool, which of three protection modes applies: Shield the tool, Shield the model, and Shield the document.</p> <table border="1px" width="100%" cellpadding="10px"> <tbody> <tr> <td><strong>Mode</strong></td> <td><strong>What happens</strong></td> <td><strong>Who sees real data</strong></td> <td><strong>How it works</strong></td> <td><strong>Typical use</strong></td> </tr> <tr> <