The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides the obsidian eval command, which allows for the execution of arbitrary JavaScript code within the context of the running Obsidian application.
[DATA_EXFILTRATION]: The skill can access sensitive user data through commands like obsidian read for file contents and obsidian dev:screenshot for capturing visual information from the Obsidian app.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from local vault files which could contain malicious instructions.
Ingestion points: Commands such as obsidian read, obsidian daily:read, and obsidian search retrieve content from the user's vault.
Boundary markers: No specific boundary markers or instructions to treat vault content as untrusted are defined in the command descriptions.
Capability inventory: The skill possesses the ability to write to the filesystem (obsidian create), execute JavaScript (obsidian eval), and take screenshots (obsidian dev:screenshot).
Sanitization: Content fetched from the vault is not sanitized or escaped before being processed by the agent.

obsidian-cli