The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the lark-cli binary to perform various operations including fetching document content, listing records from databases, and creating new documents or slides. These commands are essential for the skill's documented functionality.
[EXTERNAL_DOWNLOADS]: The skill references external documentation and configuration files located in the larksuite/cli repository on GitHub. These references are used to guide the agent's behavior and are from a well-known service related to the tool being used.
[INDIRECT_PROMPT_INJECTION]: (1) Ingestion points: Data is ingested from external Lark documents, spreadsheets, and multidimensional tables (Base) via lark-cli commands. (2) Boundary markers: Variable placeholders like {{name}} are used for data interpolation, but no specific security delimiters or 'ignore' instructions are implemented to prevent the agent from acting on instructions found within the source data. (3) Capability inventory: The agent can create new documents, slides, and drive shortcuts based on the processed data. (4) Sanitization: No explicit sanitization or validation of the fetched data is performed before it is used to generate new content.

lark-workflow-doc-template-engine