The Agent Skills Directory

[SAFE]: The skill implements a local search engine (BM25) to query UI/UX guidelines and design patterns stored in CSV and JSON files within the skill's data directory. No external network requests are performed by the core logic.
[SAFE]: The persistence logic in scripts/design_system.py includes a safe_slug function that strictly sanitizes user-provided project and page names. This prevents path traversal attacks by collapsing any potentially dangerous characters (like '../') into hyphens.
[SAFE]: The skill uses subprocess.run and subprocess.Popen exclusively within its unit test suite (scripts/tests/) to verify CLI argument handling. These calls are limited to executing the skill's own search script using the system's Python interpreter.
[SAFE]: No use of dangerous functions such as eval(), exec(), or pickle.load() was found in the codebase. Data parsing is handled via standard json.loads() and csv.DictReader().
[SAFE]: References to external resources (such as Angular, React, and Google Fonts documentation) point to well-known, official domains. No hardcoded credentials or data exfiltration patterns were detected.

ui-ux-pro-max