The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on external binaries lark-cli and whiteboard-cli to perform all document operations, including searching, fetching, creating, and updating content, as well as media orchestration.
[EXTERNAL_DOWNLOADS]: The skill facilitates downloading media (images, files, and whiteboard thumbnails) from Lark's infrastructure via +media-download. It also allows the agent to provide external URLs in +create or +update commands, which causes the Lark platform to fetch content from those remote sources.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Lark documents and Wiki nodes, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Document content, Wiki node information, and search results are retrieved via lark-cli docs +fetch and lark-cli docs +search as documented in references/lark-doc-fetch.md and references/lark-doc-search.md.
Boundary markers: There are no specified delimiters or "ignore" instructions defined for separating fetched document content from the agent's instructions.
Capability inventory: The skill possesses extensive capabilities including network operations (Lark API calls), document modification (append, overwrite, delete), and privilege management (granting user access via bot identity).
Sanitization: The documentation does not describe any sanitization or filtering of document content before it is presented to the agent's context.

lark-doc