The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes arbitrary markdown content and renders it into an HTML report, creating a potential surface for indirect prompt injection.
Ingestion points: The markdown argument in SKILL.md is the entry point for untrusted data from upstream skills or users.
Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore embedded instructions within the input data.
Capability inventory: The skill uses the Write tool to create files and the Bash tool to execute shell commands (auto-opening the file).
Sanitization: The instructions do not specify any logic for sanitizing or escaping the input markdown before it is rendered into the HTML templates.
[EXTERNAL_DOWNLOADS]: The skill fetches typography and diagramming resources from well-known and trusted external services.
Evidence: Templates and references/fonts.md link to https://fonts.googleapis.com, https://fonts.gstatic.com, and https://cdn.jsdelivr.net for font assets.
Evidence: The skill optionally fetches the Mermaid library from https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs for diagram rendering in specific audience tiers.
[COMMAND_EXECUTION]: The skill automatically executes platform-specific shell commands to open the generated report for the user.
Evidence: The Bash tool is used to run open, xdg-open, or start on the resulting file path depending on the host operating system.

moai-domain-html-report