The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface when performing weekly reviews or summarizing notes.
Ingestion points: The agent reads user-controlled data from existing files via obsidian_get_daily_note and obsidian_list_notes in SKILL.md.
Boundary markers: The instructions do not specify delimiters or provide warnings for the agent to ignore instructions embedded within the retrieved notes.
Capability inventory: The skill allows reading vault content and appending logs using obsidian_append_daily_log.
Sanitization: There is no logic provided to sanitize or filter the content of notes before the agent processes and summarizes them.

journal