The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it processes data from an external registry.
Ingestion points: The skill fetches registry metadata and component lists from https://pro.beui.dev/r/registry.json and https://pro.beui.dev/r using curl in SKILL.md.
Boundary markers: No specific delimiters or instructions are provided to the agent to disregard potential instructions embedded within the component descriptions or source code fetched from the registry.
Capability inventory: The skill uses curl for network access and npx shadcn (along with pnpm dlx and bunx) for file system modifications and package installation in SKILL.md.
Sanitization: The skill lacks explicit sanitization or validation logic for the external content before it is processed by the agent or written to the project.
[EXTERNAL_DOWNLOADS]: The skill is designed to download UI component configurations and source code from https://pro.beui.dev and https://beui.dev. These domains are vendor-owned resources used for the legitimate purpose of serving a component registry.
[COMMAND_EXECUTION]: The skill relies on shell commands to function, including curl for API interactions and npx shadcn for component installation. These commands utilize the BEUI_PRO_TOKEN environment variable for authentication headers.

beui-pro