The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of the obsidian CLI tool on the local system to manage notes, search vault content, and develop plugins.
[DYNAMIC_EXECUTION]: The skill exposes the obsidian eval code="..." command, which allows the agent to execute arbitrary JavaScript code within the context of the running Obsidian application. This is a powerful feature intended for plugin development but can be abused to perform unauthorized actions within the app.
[INDIRECT_PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection because it reads and processes data from external sources (Obsidian vault notes).
Ingestion points: Vault content is ingested via commands like obsidian read and obsidian search (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters mentioned to prevent the agent from following instructions embedded within the notes it reads.
Capability inventory: The skill can execute arbitrary JavaScript (obsidian eval), write files (obsidian create, obsidian append), and capture screenshots (obsidian dev:screenshot).
Sanitization: No sanitization or validation of the content read from the vault is described before it is processed or used in other commands.

obsidian-cli