The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several CLI tools including git, gh (GitHub CLI), cf, and npx to perform repository creation, authentication checks, and deployment tasks.
[EXTERNAL_DOWNLOADS]: Instructions include fetching skill-related files and logic directly from the author's GitHub repository (Melvynx/ai-maxxing-skills) using curl when operating from a remote context.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided descriptions, testimonials, and business briefs to generate website copy. This creates an attack surface where malicious user input could attempt to redirect agent behavior during the copy generation or scaffolding steps.
Ingestion points: User-provided argument-hint and the brief processed in Step 2 and Step 3.
Boundary markers: None identified in the prompt templates.
Capability inventory: Subprocess execution via git, gh, cf, and npx in SKILL.md.
Sanitization: No explicit sanitization or escaping of user-provided content is defined before interpolation into the generation process.

create-landing