The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from meeting transcripts and voice memos stored in ~/vault/meetings/. This content is considered untrusted as it may contain instructions that could attempt to influence the agent's behavior when the files are searched or read. \n
Ingestion points: Markdown files located in ~/vault/meetings/ and its subfolders, accessed via the minutes tool. \n
Boundary markers: Absent. The skill does not provide instructions to the agent on how to delimit transcript content from system instructions, nor does it include warnings to ignore instructions embedded within the data. \n
Capability inventory: The skill utilizes shell-based tools including the minutes search utility, cat for reading full file contents, and date for calculating ISO timestamps. \n
Sanitization: Absent. There is no evidence of content filtering, escaping, or validation performed on the transcripts before they are presented to the agent.

meetings-search