The Agent Skills Directory

[PROMPT_INJECTION]: The skill reads and processes content from Markdown files within an Obsidian vault, which presents a surface for indirect prompt injection if the files contain malicious instructions.
Ingestion points: Reads Markdown file content through search tools and file operations as defined in SKILL.md.
Boundary markers: No explicit delimitation or instruction to ignore embedded directives is used when processing file content.
Capability inventory: The skill uses rg, find, grep, and file write operations.
Sanitization: No specific content filtering or sanitization of external data is performed.
[COMMAND_EXECUTION]: The skill utilizes local system utilities such as rg (ripgrep), find, and grep for file and text discovery. These commands are executed relative to a vault path that is first verified by searching for the presence of the .obsidian configuration directory.

obsidian-vault