The Agent Skills Directory

[SAFE]: The skill uses the belt CLI tool which is authored by the same vendor (halt-catch-fire/inference-sh). Commands like belt login and belt app run are standard functionality for this ecosystem.
[EXTERNAL_DOWNLOADS]: The skill references a configuration/installation guide from https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. This is an official repository from the vendor and is considered safe.
[COMMAND_EXECUTION]: The provided code snippets demonstrate using belt to run specific applications (tavily/search-assistant, x/post-create, infsh/html-to-image, falai/flux-dev-lora). These are legitimate tool invocations within the defined scope of content creation.
[SAFE]: No obfuscation, data exfiltration, or malicious prompt injection patterns were detected. The skill follows best practices for technical documentation.

linkedin-content