The Agent Skills Directory

[Indirect Prompt Injection Surface]: The skill is designed to ingest and analyze external codebase data (Phase 0: Discovery) to extract tokens and components. This creates a potential surface where malicious instructions embedded in codebase comments or files could influence the agent's behavior during the generation process. However, this is the core intended functionality of the skill, and it includes robust mitigations such as mandatory user checkpoints at every phase and manual verification of generated content through screenshots and metadata inspections.

figma-generate-library