The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references installation guidelines and configuration files from the service provider's official GitHub repository (inference-sh/skills).- [PROMPT_INJECTION]: The skill processes external image URLs, which is a potential surface for indirect prompt injection common to image processing tasks.
Ingestion points: Image URLs are passed as arguments to the belt CLI tool within the SKILL.md examples.
Boundary markers: No specific boundary markers or 'ignore' instructions are present in the command templates.
Capability inventory: Command execution is appropriately restricted to the belt binary using the allowed-tools frontmatter configuration.
Sanitization: Input validation and content safety filtering are managed by the external inference service at runtime.

image-upscaling