The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data from notes within a vault, which constitutes a minor attack surface for indirect prompt injection common to all text-processing tools.
Ingestion points: Reads daily notes, weekly notes, linked notes, and the file AGENTS.md into the agent context (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested notes.
Capability inventory: The skill uses file-read tools and a 'vault' safe-write flow to modify existing notes (SKILL.md).
Sanitization: There is no mention of content sanitization or filtering before processing notes.

weekly-review