The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest data from a shared Obsidian vault at ~/Documents/obsidian-vault/ to provide context and persistent memory. This configuration presents a surface for indirect prompt injection if malicious instructions are embedded in the notes.
Ingestion points: Markdown files, daily notes, and search results retrieved from ~/Documents/obsidian-vault/.
Boundary markers: None. The instructions do not define specific delimiters or guide the agent to ignore instructions contained within the notes.
Capability inventory: The skill allows the agent to use Read, Write, Glob, Grep, and Edit tools within the specified vault directory.
Sanitization: The skill does not perform any validation or sanitization of the markdown content before processing.

pkm