The Agent Skills Directory

[SAFE]: The skill performs local transformations on Markdown files by reading frontmatter from notes and updating a Kanban board file. No malicious behavior was identified.
[COMMAND_EXECUTION]: The skill provides a Python script and usage instructions. The script itself is self-contained, using only the Python standard library, and does not execute shell commands or spawn sub-processes.
[DATA_EXFILTRATION]: There are no network operations or data exfiltration patterns. The script's activity is restricted to reading and writing local files.
[PROMPT_INJECTION]: The skill processes content from Markdown files, which represents an indirect prompt injection surface.
Ingestion points: Reads the content of the target Kanban board and any linked notes (via board_path.read_text and note_path.read_text in enrich_kanban_board.py).
Boundary markers: Absent; the script parses the file content directly.
Capability inventory: The script has the capability to write to the Kanban board file (board_path.write_text).
Sanitization: The script performs basic sanitization by escaping Markdown characters in aliases and URL-encoding thumbnail paths.

obsidian-enrich-kanban