The Agent Skills Directory

[SAFE]: The skill provides documentation and usage examples for the inference.sh image generation service. The instructions and linked resources are consistent with the skill's intended purpose.
[EXTERNAL_DOWNLOADS]: The skill references installation guides and secondary skill modules hosted on the service provider's official GitHub repository. These references are necessary for the platform's operation and originate from expected sources.
[COMMAND_EXECUTION]: The skill provides example commands for the belt CLI tool to perform text-to-image and image-to-image tasks. This tool usage is appropriate for the skill's functionality.
[PROMPT_INJECTION]: The skill processes user-provided prompts and image URLs through the belt CLI tool, which constitutes an entry point for untrusted data into the image generation pipeline.
Ingestion points: prompt and image_url fields within JSON input for belt app run commands (SKILL.md)
Boundary markers: Tool inputs are structured within JSON objects
Capability inventory: Shell execution limited to the belt command utility (SKILL.md)
Sanitization: No explicit sanitization or input validation is performed within the skill instructions

ai-image-generation