The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references installation guidelines and additional configuration files hosted on the official inference-sh GitHub repository. These are standard resources for utilizing the inference.sh platform.
[COMMAND_EXECUTION]: The skill instructs the agent to use the belt CLI tool for image processing tasks. The execution environment is restricted by the allowed-tools frontmatter property, which limits tool access to specific belt commands.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection as it processes external image URLs.
Ingestion points: The image_url parameter used in the belt app run commands within SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in the prompt templates.
Capability inventory: The skill is capable of executing belt commands via the Bash tool.
Sanitization: There is no explicit sanitization or validation of the input URLs described in the instructions.
Note: This is a standard risk for skills processing external data, and the specialized nature of the image upscaling models reduces the likelihood of successful exploitation.

image-upscaling