The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill dynamically fetches the markmap-cli tool from the official NPM registry using npx if it is not already installed locally. This is a common practice for Node.js-based utilities to manage binary dependencies.
[COMMAND_EXECUTION]: The main.py script uses the subprocess.run method to execute the conversion command. It passes arguments as a list, which is a secure way to prevent shell injection vulnerabilities.
[INDIRECT_PROMPT_INJECTION]: The skill processes Markdown headings and generates interactive prompts that a user can copy and send back to the agent. This creates a potential feedback loop for untrusted data generated by the model.
Ingestion points: The skill reads Markdown content from the file path provided in the --input argument within main.py.
Boundary markers: There are no specific delimiters or 'ignore' instructions for the content being processed.
Capability inventory: The skill has the ability to execute shell commands (subprocess.run) and write to the local file system to generate the output HTML and copy KaTeX fonts.
Sanitization: The JavaScript injected into the HTML uses textContent to display node titles in the prompt UI, which prevents basic HTML/XSS injection, but it does not filter the semantic content of the Markdown headings.

mindmap