The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/setup.py and scripts/lib/client.py files use subprocess.run to execute AWS CLI commands (such as aws rds generate-db-auth-token and aws sts get-caller-identity) and Python's pip manager. These operations are essential for authenticating with AWS services and managing database connections. Additionally, scripts/setup.py reads local AWS configuration files to list profiles, which is a standard procedure for AWS-integrated tools.
[EXTERNAL_DOWNLOADS]: The scripts/setup.py file installs the psycopg2-binary library from the official Python Package Index (PyPI) if it is missing. This is a standard and well-known dependency for PostgreSQL interaction in Python.
[PROMPT_INJECTION]: The skill ingests data from external AWS RDS databases via scripts like query.py and sample.py. This creates a surface for indirect prompt injection if an attacker controls the database content.
Ingestion points: Database query results are loaded into the agent's context through scripts in the scripts/ directory.
Boundary markers: The skill does not implement specific boundary delimiters for processed database data, but provides strict SQL formatting instructions to the agent.
Capability inventory: Subprocess calls for AWS CLI and pip are present in scripts/setup.py and scripts/lib/client.py.
Sanitization: The validate_sql function in scripts/lib/client.py prevents multi-statement queries and enforces write-mode constraints.

rds