The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes local Python scripts (profile_store.py, validate_skill.py) intended for managing user profiles and validating the skill's file structure. The profile_store.py script specifically implements a security check (SENSITIVE_PARTS) that prevents the persistent storage of sensitive data such as API keys, tokens, or passwords within the user profile records.
[EXTERNAL_DOWNLOADS]: The documentation and references point to external assets from trusted organizations and well-known services, such as the GSAP animation library (gsap.com) and the vendor's official GitHub organization and website (lovstudio.ai). These are used for documentation, installation, and runtime animation capabilities.
[INDIRECT_PROMPT_INJECTION]: As a design tool, the skill is designed to ingest and process untrusted external data, such as project source code and user-provided media assets. While this creates a surface for indirect prompt injection, the skill's instructions mandate adherence to established design systems and prioritize explicit user statements over inferred context, reducing the risk of autonomous obedience to embedded instructions.

lov-frontend-design