The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes an installation script scripts/install_all.py that utilizes subprocess.run to execute shell commands. This script is designed to install the relevant sub-skills for the database ecosystem using a local CLI utility. The command arguments are derived from a hardcoded list of skill names within the script and do not process external or untrusted user input, mitigating command injection risks.
[PROMPT_INJECTION]: The SKILL.md file contains directive instructions, such as 'MUST consult' and 'Do not hallucinate', which are intended to provide architectural constraints for an orchestrator-style agent. These instructions are standard for defining operational boundaries and do not attempt to bypass safety protocols or override the agent's core system instructions.

ecosystem-database