# Amazon — Protect agent tool calls with Skyflow and Amazon Bedrock AgentCore Gateway

- Company: Amazon (amazon.com)
- Announced: 2026-11-19T18:14:36+00:00
- Category: not stated
- Coverage: 1 outlet
- Announcement: no
- Group: covered
- Source: https://aws.amazon.com/blogs/machine-learning/protect-agent-tool-calls-with-skyflow-and-amazon-bedrock-agentcore-gateway/
- Record: https://forck.live/items/38782-protect-agent-tool-calls-with-skyflow-and-amazon-bedrock-agentcore-gateway
- Subject: Bedrock / Nova

Amazon's post shows how to attach Skyflow Detect to Amazon Bedrock AgentCore Gateway as a request and response interceptor so sensitive data stays out of agent tool calls and model context. The interceptor de-identifies data before it reaches a tool, restores it before the agent reads the result, and swaps documents for clean copies, without changing agent or tool code. It runs as a single AWS Lambda function on the gateway's REQUEST and RESPONSE interception points, calling Skyflow Detect to find names, emails, phone numbers, government IDs, card numbers, dates of birth and locations and replace them with tokens. Skyflow Vault stores the originals so authorized systems can reverse the tokens, and the configuration sets direction, entity types and token type per server and per tool. The policy lives in AWS Systems Manager Parameter Store, so changes take effect without redeploying, and the interceptor fails closed, withholding calls it cannot de-identify and fetching files only from allowlisted locations. Skyflow is available in AWS Marketplace and the interceptor is open source on GitHub.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/protect-agent-tool-calls-with-skyflow-and-amazon-bedrock-agentcore-gateway/:

> 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.

## Around this story

Outlets this record can name and link:

- Neoteo — Skyflow AgentCore data protection: how it works: https://neoteo.com/en/how-skyflow-protects-data-in-amazon-bedrock-agentcore

---

Record: https://forck.live/items/38782-protect-agent-tool-calls-with-skyflow-and-amazon-bedrock-agentcore-gateway
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
