AWS Secrets Manager introduces safe secrets handling in the Agent Toolkit for AWS
News
AWS Secrets Manager introduces a secret safety skill as part of the Agent Toolkit for AWS, enabling secure secret handling in AI coding agent workflows.
- Agents can retrieve and use secrets without exposing plaintext values to the model or session logs
- Two-layer approach: steers agents away from requesting raw secrets and resolves references at execution time in child processes
- Ensures secrets never appear in model context, session logs, or agent memory
- Available for Claude Code, Codex, Cursor, and all AWS Regions with Secrets Manager support
- Install the aws-core plugin from the Agent Toolkit for AWS GitHub repository to get started
This enhancement protects sensitive data in agentic workflows while maintaining developer productivity.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.