aws-data

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of standard AWS CLI commands (e.g., aws dynamodb list-tables, aws elasticache describe-cache-clusters) for cloud infrastructure management.
  • [EXTERNAL_DOWNLOADS]: The skill depends on the boto3 Python library, which is the official and trusted AWS SDK.
  • [DATA_EXPOSURE]: No hardcoded credentials or sensitive local file access was detected. The skill properly demonstrates using AWS Secrets Manager ARNs for database authentication via the RDS Data API.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external AWS databases into the agent context.
  • Ingestion points: Results from DynamoDB, RDS, and Redshift queries defined in SKILL.md.
  • Boundary markers: Absent; no specific delimiters are used for external data.
  • Capability inventory: AWS CLI and boto3 SDK for reading and writing data in AWS environments.
  • Sanitization: Absent; the skill does not specify validation for data retrieved from AWS services.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 07:12 AM
Security Audit — agent-trust-hub — aws-data