connecting-to-data-source

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Dynamic Script Generation: The skill provides a Python script template in references/troubleshooting.md for engine-level connection verification. It instructs the agent to write this script to an S3 bucket and execute it as an AWS Glue job. While this is a functional diagnostic tool, it involves creating and running executable code generated from a template at runtime.
  • Indirect Prompt Injection Surface: The skill discovers existing databases and clusters using commands like aws rds describe-db-instances. The information returned from these AWS APIs is used to present options to the user. This represents a potential surface where resource metadata could be used for indirect prompt injection, though the risk is low given the trusted nature of the data source.
  • System Command Execution: The workflow involves executing various AWS CLI commands and network diagnostic tools such as telnet and nc to troubleshoot connectivity. These commands are necessary for the skill's stated purpose of database connection management but involve direct interaction with the host environment's shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:26 PM
Security Audit — agent-trust-hub — connecting-to-data-source