The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from external multidimensional tables which may contain untrusted content capable of influencing the agent's behavior during analysis.
Ingestion points: Data is ingested via lark-cli base +record-list and lark-cli base +record-search as described in SKILL.md.
Boundary markers: The instructions do not define explicit boundary markers or delimiters to separate data from instructions.
Capability inventory: The skill possesses the capability to write to external documents using lark-cli docs +create and modify dashboards via lark-cli base +dashboard-arrange.
Sanitization: No sanitization or escaping mechanisms are specified for the data processed by the AI analysis engine.
[COMMAND_EXECUTION]: The skill makes extensive use of the lark-cli system binary to perform operations such as authentication (auth login), data retrieval (base +data-query), and report generation (docs +create).
[EXTERNAL_DOWNLOADS]: The skill references and fetches instructional content and security guidelines from the official GitHub repository for the larksuite CLI tooling.

lark-workflow-base-analytics