The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing a third-party utility from a personal GitHub repository.
Evidence: SKILL.md instructions specify installation via brew tap antoniorodr/memo.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes text from Apple Notes, which is an external data source that could contain malicious instructions.
Ingestion points: memo notes commands in SKILL.md that list, search, and view note content.
Boundary markers: Absent; the instructions do not include delimiters or warnings for the agent to ignore instructions embedded in the notes.
Capability inventory: The skill can execute CLI commands, create/edit/delete notes, and export note content to files (documented in SKILL.md).
Sanitization: Absent; there is no mention of filtering or sanitizing note content before processing.
[COMMAND_EXECUTION]: The skill's primary functionality is implemented by executing the memo command-line utility.
Evidence: All actions described in SKILL.md (viewing, creating, editing, deleting, moving, and exporting notes) are performed via memo commands.

apple-notes