The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands including grep, find, sed, awk, and mv to manipulate vault files, and utilizes the obsidian-cli for API-driven interactions with Obsidian.
[DYNAMIC_EXECUTION]: The skill is designed to generate multi-step Bash and Python scripts based on user requirements to perform automated vault maintenance and note processing.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by processing markdown content from the vault, which could potentially contain malicious instructions affecting the script generation or command execution flow.
Ingestion points: Markdown files (.md) within the Obsidian vault processed by the agent (SKILL.md).
Boundary markers: None explicitly implemented to separate data from instructions.
Capability inventory: Shell command execution, Python runtime access, and Local REST API control via CLI.
Sanitization: Lacks explicit sanitization logic for vault content before it is interpolated into scripts or commands.

obsidian-automation