The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill establishes a connection to a remote Model Context Protocol (MCP) endpoint at https://kling.ai/mcp/plugin. This connection is used to fetch live tool definitions and route generation requests to the vendor's cloud infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (API responses for elements, motions, and tasks), which represents a vulnerability surface for indirect prompt injection.
Ingestion points: Data enters the agent context through the outputs of the element_list, motion_library_list, and query_tasks tools.
Boundary markers: The skill utilizes structured JSON-array strings for element bindings and specific prompt placeholders like <<<ELEMENT_ID>>> to differentiate data from instructions.
Capability inventory: The skill has access to generation tools, file upload mechanisms, and resource management operations including element_delete.
Sanitization: The instructions require the agent to validate resource objects against a defined MCP contract, inspect resource types using element_get, and resolve unambiguous IDs before executing commands.

kling-ai