The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from existing Markdown files which represents a surface where malicious instructions embedded in document text could attempt to influence the agent during the reformatting process.
Ingestion points: The skill reads existing .md files in the repository as the first step of its workflow to understand structure and formatting.
Boundary markers: There are no explicit delimiters or 'ignore' instructions defined in the skill to isolate the text being reformatted from the agent's instructional context.
Capability inventory: The skill has the permission to create new .md files and edit existing ones across the repository (applies_to: **/*.md).
Sanitization: No specific sanitization, filtering, or text escaping is performed on the ingested file content before it is processed.

pavlo-markdown-editor