The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard linting and validation commands including npm run lint:markdown, markdownlint --fix, and the project-specific astrofy docs check. These are standard developer operations for documentation maintenance.
[INDIRECT_PROMPT_INJECTION]: The skill processes Markdown and MDX files from the project repository, which could potentially contain malicious instructions designed to influence the agent during the linting process. This is an inherent risk when processing untrusted local content.
Ingestion points: Project .md and .mdx files.
Boundary markers: The instructions do not specify explicit delimiters to isolate the content of the files being processed.
Capability inventory: File system access and shell command execution via npm, markdownlint, and astrofy.
Sanitization: No specific content sanitization or escaping steps are defined prior to processing.

astrofy-markdown