The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the execution of lark-cli to fetch meeting details and transcripts. It passes parameters such as note_id and doc_token directly to CLI commands.
[PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection due to its processing of untrusted data.
Ingestion points: The skill ingests note_id, note_doc_token, and verbatim_doc_token which may originate from external documents or user-provided content.
Boundary markers: Absent. There are no delimiters or instructions to ignore potential commands embedded within the data retrieved from the Lark platform.
Capability inventory: The skill utilizes lark-cli for network-based queries and writes output to the local filesystem (e.g., ./notes/{note_id}/unified_transcript.md).
Sanitization: No explicit sanitization, validation, or escaping of the ingested meeting data is performed before it is processed or written to disk.

lark-note