Enforcing User Authorization Context in Amazon Bedrock AI Agents
AWS details a pattern for propagating user authorization context within AI agents built with Amazon Bedrock AgentCore. This approach ensures agents only access data users are authorized to see, preventing unauthorized data exposure and protecting against prompt injection. It employs Amazon Cognito, Bedrock AgentCore Identity, AWS IAM, and session tags to enforce least privilege across services like DynamoDB, S3-backed Knowledge Bases, and external SaaS platforms like Salesforce. The architecture emphasizes the agent as an orchestrator, shifting authorization enforcement to downstream services.
Notes (1) ›
- Pattern for User Authorization Context in Bedrock AI Agents
AWS introduces a best practice pattern for securely propagating user authorization context in AI agents built with Amazon Bedrock AgentCore. This architecture uses Amazon Cognito and AWS STS session tags to enforce least privilege access to various data sources like DynamoDB, S3-backed Knowledge Bases, and external services such as Salesforce, without requiring authorization logic within the agent itself.
https://aws.amazon.com/blogs/security/propagate-user-authorization-context-in-ai-agents-with-amazon-bedrock-agentcore/
Related releases
- Amazon DynamoDB Streams now supports attribute-based access control (ABAC) AWS What's New ·
- Amazon DynamoDB adds general availability for real-time vector search AWS What's New ·
- DynamoDB adds real-time vector search for scalable similarity searches AWS News Blog ·
- DynamoDB Mapper for Kotlin Now Generally Available on AWS AWS Developer Tools Blog ·
- Amazon GameLift Streams adds IAM role credentials for secure resource access AWS What's New ·
- AWS Glue adds SAP OData connector and zero-ETL to GovCloud regions AWS What's New ·