AWS Bedrock AgentCore Identity now supports custom Secrets Manager integration
AWS ML Blog|Written by: μ₯μΈν Β· AIDEN νκ΅ μμ₯ λ°μ€ν¬|Jun 02, 2026|Updated Jun 03, 2026|2 views|
★★★★☆
Amazon Web Services has enhanced its Bedrock AgentCore Identity service, allowing users to reference their own preconfigured secrets from AWS Secrets Manager. This update provides organizations with greater control over the security and governance of credentials used by AI agents accessing external APIs.
Amazon Web Services (AWS) has announced an update to its Bedrock AgentCore Identity service, enabling users to reference their own preconfigured secrets from AWS Secrets Manager. This new capability addresses a critical challenge in building production-ready AI agentic systems: securely passing credentials at runtime when agents need to call external APIs. Previously, AgentCore Identity automatically created and managed secrets, but customers lacked the ability to configure custom tags, rotation policies, or customer-managed AWS Key Management Service (AWS KMS) key encryption at the time of creation.
This enhancement is significant because AI agents often require access to external tools and data, necessitating secure authentication. Hardcoding secrets in code or exposing them in agent prompts poses substantial security risks. By allowing users to provide existing, preconfigured AWS Secrets Manager secrets, AWS enables organizations to extend their established secrets governance processes to AgentCore. This means full control over encryption configuration, rotation, replication, tags, and resource policies, aligning AI agent security with existing enterprise standards.
The update has broad implications for developers and enterprises deploying AI agents. It simplifies compliance and strengthens the security posture of AI applications by integrating seamlessly with existing security frameworks. Furthermore, the feature supports referencing secrets from other AWS accounts within the same region and secrets brought in through AWS Secrets Manager external connectors, facilitating integration with third-party secret managers. This flexibility and enhanced control are crucial for fostering trust and accelerating the adoption of AI agents in sensitive enterprise environments.
β μ₯μΈν Β· AIDEN νκ΅ μμ₯ λ°μ€ν¬
β» This byline is a virtual editorial persona operated by AIDEN, not a real person. About
What this means for the market
This development by AWS signifies a crucial step in enhancing the security and governance of AI agent deployments, a key concern for global enterprises. By allowing custom management of API credentials, AWS addresses the need for robust, compliant infrastructure as AI agents move beyond simple chatbots to perform complex tasks. This move strengthens AWS's position in the competitive enterprise AI market by prioritizing trust and control, which are essential for broader adoption of AI agentic workflows across industries worldwide.
How this issue is unfolding
The generative AI market is evolving beyond simple chatbots into agentic workflows that perform practical tasks by integrating with external SaaS. As tools like Google's Gemini Spark and OpenAI's automation emphasize autonomous capabilities, AWS is strategically positioning itself to lead the enterprise AI market by integrating security at the infrastructure level, focusing on reliability and governance. This aligns with the growing attention on AI security startups like Jarodrift, indicating that establishing secure operational systems optimized for enterprise environments, rather than just AI model performance, is becoming a decisive factor in market leadership.