The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands, specifically find and a Grep utility, to perform file searches within the user's local vault path. These commands are restricted to the local file system.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of markdown files within the user's Obsidian vault. If these files contain instructions designed to influence the agent's behavior, those instructions might be followed if included in the conversation context without proper delimiters.
Ingestion points: Markdown files (.md) located within the user-configured Obsidian vault (SKILL.md)
Boundary markers: None specified in the instructions to separate note content from agent instructions
Capability inventory: The skill utilizes Grep and find to access and retrieve file content (SKILL.md)
Sanitization: No sanitization or content filtering is described in the provided instructions

obsidian-search