The Agent Skills Directory

[Prompt Injection] (SAFE): The skill contains only legitimate instructions for utilizing the WordPress Design System and lacks any patterns suggesting safety filter bypasses or role-play jailbreaks.- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive file paths, or unauthorized network operations were identified. The use of the wpds:// protocol for local MCP server communication is a standard integration pattern.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill references established WordPress UI packages (@wordpress/components, @wordpress/ui) and does not attempt to download or execute external scripts at runtime.- [Indirect Prompt Injection] (SAFE): While the skill processes UI-related user requirements, it includes clear boundary markers to limit the scope of operations to UI components and tokens, reducing the risk of processing malicious data payloads.

wpds