aws-data

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents various AWS CLI commands (e.g., aws dynamodb list-tables, aws elasticache describe-serverless-caches) used to manage and query cloud database resources directly from the shell.
  • [PROMPT_INJECTION]: The skill operates on data retrieved from external AWS services, which creates a potential surface for indirect prompt injection if those services contain untrusted content.
  • Ingestion points: Data retrieved from DynamoDB, Aurora, Redshift, Neptune, and S3 Tables via boto3 and aws CLI (SKILL.md).
  • Boundary markers: None; the agent is not explicitly instructed to treat the database results as untrusted content.
  • Capability inventory: The agent can execute shell commands via the aws CLI and run Python code using the boto3 SDK (SKILL.md).
  • Sanitization: No input sanitization or output encoding is demonstrated in the provided reference snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 03:29 AM
Security Audit — agent-trust-hub — aws-data