finding-data-lake-assets

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Dynamic Script Generation: For advanced search scenarios where standard CLI calls are insufficient, the skill generates and executes a localized Python script using the AWS SDK (boto3). This is used to perform efficient, paginated searches across multiple Glue databases in a single operation, reducing network overhead and token usage.
  • Cloud Infrastructure Interaction: The skill utilizes the AWS CLI and SQL queries to interact with Glue, S3, and Redshift. It incorporates security best practices by recommending identity verification via sts get-caller-identity and prioritizing sandboxed AWS MCP server tools when available.
  • Data Processing Considerations: The skill processes metadata retrieved from AWS catalogs, such as table names and column descriptions. As a standard practice for skills that ingest external data, the agent is instructed to use this information for resource resolution, maintaining a clear boundary between technical metadata and operational instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:02 AM