The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and format content within an Obsidian vault, which involves reading and writing to files that may contain untrusted data.
Ingestion points: The skill reads from various directories including Sources/, Knowledge/, Experiments/, and Maps/ as defined in references/CANVAS.md and references/OBSIDIAN-MARKDOWN.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat vault content as potentially adversarial data.
Capability inventory: The skill has capabilities to write files (.canvas, .base, .md) and execute commands via the obsidian CLI (searching, reading, and appending).
Sanitization: The instructions do not specify any sanitization or validation logic for the content retrieved from the vault.
[COMMAND_EXECUTION]: The skill leverages a local CLI tool for vault management operations.
Evidence: references/CLI.md provides examples of shell commands such as obsidian search query="..." and obsidian read file="..." for navigating and editing the knowledge base.

obsidian-kb-artifacts