The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for using the obsidian CLI tool to execute local system commands that interact with the Obsidian application.
[DYNAMIC_EXECUTION]: The obsidian eval command allows for the execution of arbitrary JavaScript code within the context of the running Obsidian instance. While documented for plugin development, this constitutes a mechanism for dynamic code execution.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and retrieval of data from an Obsidian vault, creating a potential surface for indirect prompt injection.
Ingestion points: Data is ingested through obsidian create and obsidian append commands as described in SKILL.md.
Boundary markers: The skill lacks explicit boundary markers or instructions to treat data appended to the vault as untrusted content.
Capability inventory: The tool possesses capabilities for reading and writing files (read, create, append), inspecting application state (dev:dom, dev:screenshot), and executing code (eval) as documented in SKILL.md.
Sanitization: No sanitization or validation logic is defined for data processed by these commands.

obsidian-cli