The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill exposes the obsidian eval command, which allows the agent to execute arbitrary JavaScript code within the context of the running Obsidian application (e.g., obsidian eval code="..."). This provides a high-privilege execution environment for the agent.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with user-controlled data within Obsidian vaults, creating a vulnerability surface for indirect prompt injection.
Ingestion points: Commands like obsidian read, obsidian search, obsidian daily:read, and obsidian dev:dom ingest content from the user's vault or the application's DOM into the agent's context.
Boundary markers: None. The skill does not define specific delimiters or instructions to the agent to treat vault content as untrusted data.
Capability inventory: The skill possesses powerful capabilities including file system modification (obsidian create, obsidian append, obsidian dev:screenshot) and arbitrary JavaScript execution (obsidian eval).
Sanitization: None. Data fetched from the vault is passed to the agent without filtering or sanitization.
[COMMAND_EXECUTION]: The skill operates by executing commands via the obsidian CLI tool on the host system. While this is the intended purpose, it grants the agent the ability to invoke shell commands that interact with the application and local files.

obsidian-cli