The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content from various files in the vault to generate synthesized summaries, creating a potential surface for indirect instructions to influence agent behavior.
Ingestion points: Recent files in 01-daily/briefs/, 02-personal/braindumps/, 03-professional/braindumps/, 04-projects/*/braindumps/, 01-daily/checkins/, and 00-inbox/MY-PROFILE.md.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers when processing the scanned files.
Capability inventory: The skill utilizes shell execution (date) and file writing (01-daily/checkins/weekly-checkin-YYYY-MM-DD.md).
Sanitization: There is no mention of sanitization or validation for the content ingested from the markdown files.
[COMMAND_EXECUTION]: The skill requires executing the date command via Bash to retrieve an accurate timestamp for the generated check-in document's frontmatter.

weekly-checkin