The Agent Skills Directory

[SAFE]: The skill is primarily documentation-based, providing architectural patterns and trade-off analysis for cloud systems. All references point to local files within the skill folder.
[COMMAND_EXECUTION]: The provided script scripts/pattern-shortlist.py is a benign tool that uses the standard library (argparse, json) to filter a static dictionary of patterns based on user input. It does not perform network operations, file writes, or sensitive system calls.
[EXTERNAL_DOWNLOADS]: No remote dependencies or external downloads are initiated by the skill or its scripts.
[PROMPT_INJECTION]: The instructions follow best practices for AI agent guidance, focusing on structured workflows and verification protocols without attempting to bypass safety filters or override system constraints.
[DATA_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file access (e.g., .ssh, .aws), or network-based exfiltration was found.
[DYNAMIC_EXECUTION]: No dynamic code generation, eval(), or exec() patterns are present. The skill relies on static references and a simple logic-based script.

cloud-design-patterns