The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to ingest and process untrusted data from the user's Obsidian vault.\n
Ingestion points: The agent is instructed to read .base files and inspect note frontmatter properties (e.g., note.author, file.properties) as documented in SKILL.md and references/properties-and-formulas.md.\n
Boundary markers: The instructions do not specify the use of boundary markers (e.g., XML tags or delimiters) or explicit 'ignore instructions' directives when the agent processes external note content.\n
Capability inventory: The skill has the capability to write .base configuration files to the vault, which are then rendered by the Obsidian application.\n
Sanitization: While the escapeHTML() function is documented in references/FUNCTIONS_REFERENCE.md as a tool for users, the skill's workflow does not mandate its use for sanitizing note properties before they are included in formulas or views.

obsidian-bases