The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script (scripts/validate_and_render.py) that executes external rendering tools (markmap, npx, or node) using subprocess.run. This is the primary mechanism for converting Markdown mind maps into HTML files. The script uses argument lists instead of shell strings, which is a secure method for executing subprocesses.
[EXTERNAL_DOWNLOADS]: The rendering script is configured to use npx --yes markmap-cli to ensure the Markmap utility is available. This command fetches the package from the official npm registry if it is not present in the local cache, which is standard behavior for Node.js-based developer tools.
[PROMPT_INJECTION]: The skill is designed to process untrusted data from repositories, such as README.md files and source code, to generate mind map structures. This creates a surface for indirect prompt injection.
Ingestion points: The agent is instructed to read various files within a project directory (e.g., README.md, AGENTS.md, package configurations).
Boundary markers: None are explicitly used in the prompt instructions to separate source material from agent instructions.
Capability inventory: The skill can read local files and execute a validation script that spawns subprocesses.
Sanitization: The Python script performs structural validation (e.g., checking for generic labels and limiting child nodes) but does not sanitize the text content for potential malicious instructions.

markmap-analogy-mindmap