The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs users to download and run the yuque-mcp package from the npm registry using npx during installation and troubleshooting.\n- [COMMAND_EXECUTION]: Installation and usage require the execution of shell commands, including npx yuque-mcp and various CLI arguments for configuration.\n- [REMOTE_CODE_EXECUTION]: Troubleshooting instructions for Linux users include a common pattern for installing Node.js that pipes a script from nodesource.com directly into bash with elevated privileges (sudo).\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it retrieves and processes external document content and search results from the Yuque platform.\n
Ingestion points: The tools yuque_get_doc, yuque_search, and yuque_list_notes bring external text into the agent's context.\n
Boundary markers: The skill instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the document content.\n
Capability inventory: The skill has the ability to perform network requests to the Yuque API and can create or modify documents.\n
Sanitization: No explicit content sanitization or validation methods are mentioned for handling the retrieved document data.

yuque-mcp-server