The Agent Skills Directory

SAFE (SAFE): No malicious patterns detected. The skill consists exclusively of markdown documentation, design templates, and systematic workflow descriptions for UI/UX development.
Indirect Prompt Injection (SAFE): The skill defines a workflow for capturing and analyzing screenshots from external design inspiration websites (Dribbble, Behance, etc.). While processing untrusted visual data is an ingestion point, it is central to the skill's purpose and lacks specific exploitation triggers.
Ingestion points: Workflow 1 in SKILL.md captures and analyzes external website screenshots using multimodal AI tools.
Boundary markers: None explicitly defined in the provided workflow steps to separate untrusted content from system instructions.
Capability inventory: The skill relies on integrated capabilities for writing documentation, generating images, and potentially creating UI code via ui-styling and web-frameworks skills.
Sanitization: The skill assumes standard safety guardrails provided by the underlying multimodal AI system.

aesthetic