The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed entirely around executing the obsidian command-line interface to perform file system operations, search, and application control.
[DYNAMIC_EXECUTION]: The skill documents the obsidian eval command, which allows for the execution of arbitrary JavaScript code within the context of the running Obsidian application.
Evidence: obsidian eval code="app.vault.getFiles().length" in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill provides the ability to read content from an external, potentially untrusted source (an Obsidian vault) and incorporates that content into the agent's context. This creates a risk where malicious instructions embedded in a user's notes could be executed if processed by the agent.
Ingestion points: Vault content is read via obsidian read, obsidian daily:read, and obsidian search (referenced in SKILL.md).
Boundary markers: None identified in the skill instructions to separate vault data from agent instructions.
Capability inventory: The skill can write files (obsidian create, obsidian append), execute code (obsidian eval), and take screenshots (obsidian dev:screenshot).
Sanitization: No evidence of sanitization or validation of data read from the vault before processing.

obsidian-cli