The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the qmd and obsidian CLI utilities to perform searches and file operations (create/append) within the local file system, specifically targeting a `3
Resources/` directory.
[PROMPT_INJECTION]: There is a surface for indirect prompt injection because the skill reads content from existing local notes via qmd query to determine whether to append to an existing page or create a new one. Malicious instructions inside an existing note could theoretically influence this logic.
Ingestion points: Existing Obsidian notes are read during the search step via qmd query (SKILL.md).
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potential instructions embedded within the queried notes.
Capability inventory: The skill possesses file-write capabilities through obsidian create and obsidian append (SKILL.md).
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from existing notes before processing.

save-note