The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill follows its stated purpose of providing documentation and usage examples for the belt CLI.
[EXTERNAL_DOWNLOADS]: References official installation instructions and skill packages from the inference-sh and belt-sh GitHub organizations.
[COMMAND_EXECUTION]: Provides examples for using the belt CLI tool via Bash for logo generation, as well as npx for adding related skills.
[PROMPT_INJECTION]: The skill uses user input for constructing image generation prompts, which is the primary intended functionality.
Ingestion points: Prompts provided in the JSON payload of belt app run commands in SKILL.md.
Boundary markers: None; input is interpolated directly.
Capability inventory: Limited to image generation, upscaling, and CLI authentication via the belt tool.
Sanitization: No input sanitization or filtering is implemented.

logo-design-guide