The Agent Skills Directory

[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill metadata specifies the installation of obsidian-cli via a third-party Homebrew tap (yakitrak/yakitrak/obsidian-cli). This external dependency is required for the vault automation features described in the instructions.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill instructs the agent to read the Obsidian application's configuration file located at ~/Library/Application Support/obsidian/obsidian.json to identify active vault paths. This access is necessary for the skill to function and does not involve credential exfiltration.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled Markdown files, creating an attack surface for indirect prompt injection.
Ingestion points: Markdown note content is ingested through the search-content command in SKILL.md.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are included in the prompt templates.
Capability inventory: The agent has the ability to search, create, move, and delete files on the local filesystem via the obsidian-cli tool.
Sanitization: There are no sanitization or validation steps defined for the content read from the notes.

obsidian