The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the obsidian CLI to perform vault operations. While these are standard utility commands, the tool provides broad access to the local vault environment.
[COMMAND_EXECUTION]: The obsidian eval command allows for the execution of arbitrary JavaScript code (obsidian eval code="...") within the context of the running Obsidian application. This is a powerful dynamic execution capability intended for development but poses a risk if manipulated to execute malicious logic.
[PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data through commands like obsidian read and obsidian search. This creates a surface for indirect prompt injection where malicious instructions stored within Obsidian notes could influence the agent's behavior during processing.
[PROMPT_INJECTION]: Capability Inventory: The skill has the ability to read and write files via obsidian read, obsidian create, and obsidian append, and can execute application-level code via obsidian eval. These capabilities, combined with the ingestion of vault data, define the indirect injection risk surface.

obsidian-cli