← Back
AWS ML Blog

Protect agent tool calls with Skyflow and Amazon Bedrock AgentCore Gateway

•13 min read•
#agents#bedrock
Protect agent tool calls with Skyflow and Amazon Bedrock AgentCore Gateway
Level:Intermediate
For:AI Engineers
✦TL;DR

This post introduces a Skyflow Detect interceptor added to the Amazon Bedrock AgentCore Gateway that de‑identifies sensitive data on every agent‑tool request and response, restores it for the agent, and swaps out documents with clean copies before opening. The interceptor runs as an AWS Lambda function and requires no changes to existing agents or tools. Skyflow is distributed via AWS Marketplace and the interceptor code is open‑source on GitHub, giving enterprises a single, reusable control point for data protection across all agent‑tool interactions. Engineers can now enforce compliance and privacy policies centrally without modifying individual agent implementations.

⚡ Key Takeaways

  • Skyflow Detect is integrated as both a request and response interceptor in the AgentCore Gateway.
  • The interceptor de‑identifies data before it reaches a tool, restores it before the agent reads the result, and replaces documents with clean copies before opening.
  • Interceptors run as AWS Lambda functions, allowing custom code to inspect, rewrite, or block payloads.
  • Skyflow is available in AWS Marketplace and the interceptor implementation is open source on GitHub.
💡 Why It Matters

By placing a single, reusable data‑protection layer at the gateway, engineers can safeguard sensitive information across all tool calls without touching agent or tool code, simplifying compliance for production AI systems.

✅ Practical Steps

  1. Deploy the Skyflow Detect interceptor as an AWS Lambda function attached to the Amazon Bedrock AgentCore Gateway.
  2. Configure the gateway to use the interceptor for both request and response handling, ensuring payloads are de‑identified and restored automatically.

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

New in AWS Quick: More capable flows, an updated web experience, and agents that work together

AWS ML Blog•#agents

How Google Duplex evolved to also call businesses for you in Gemini

Google Research•#agents

Genie ZeroOps, now in public beta: An autonomous agent that fixes data pipelines, with lessons from 80,000 customer issues

Databricks Blog•#agents

Towards a Science of Capable Autonomous Agents & Provable Safety — Part II

CMU ML Blog•#agents

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING