The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The skill setup requires connecting to a third-party MCP server endpoint at https://rube.app/mcp. While this is the intended design for the toolkit's functionality, it involves an external dependency outside of the predefined trusted scope.
[PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) when processing data from Figma files and comments. * Ingestion points: Content is retrieved from Figma via FIGMA_GET_FILE_JSON and FIGMA_GET_COMMENTS_IN_A_FILE. * Boundary markers: The instructions do not provide delimiters or warnings to the agent to ignore instructions embedded within the retrieved Figma data. * Capability inventory: The skill includes tools for rendering images, managing comments, and extracting structured file data. * Sanitization: No sanitization or escaping of external content is specified before the data is processed by the agent.

figma-automation