The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch and execute the @bilig/workpaper package from the official NPM registry and references documentation hosted on GitHub and GitHub Pages.
[COMMAND_EXECUTION]: Uses npm exec to launch a Model Context Protocol (MCP) server for spreadsheet tasks; the instructions specifically advise the agent to use argument arrays, pin package versions, and obtain user approval before execution.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface when processing untrusted JSON workbook files and spreadsheet formulas. It provides explicit remediation guidance, instructing the agent to reject inputs containing shell metacharacters (such as backticks, semicolons, and pipes) to prevent command injection.

bilig-workpaper