The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx -p @vm0/cli to download and run the vendor-specific CLI tool from the NPM registry, which is a well-known and trusted service.
[COMMAND_EXECUTION]: The skill executes local shell commands (zero generate, zero host, zero doctor) to perform artifact generation and manage project tasks.
[PROMPT_INJECTION]: The skill processes untrusted user data to generate artifacts, identifying a common indirect injection surface area.
Ingestion points: User-provided descriptions for images, videos, and websites ingested via SKILL.md workflows.
Boundary markers: Not explicitly defined in the command construction steps.
Capability inventory: Shell execution (npx), temporary file creation, and network access for artifact delivery.
Sanitization: The skill proactively addresses injection risks by recommending that the agent write complex or sensitive prompts to temporary files and pipe them into the CLI tool rather than interpolating them directly into shell strings.