app-store-screenshots
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation documentation and related assets from the official inference-sh GitHub organization.
- [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to execute AI generation tasks, including image and video creation, through the inference.sh platform.
- [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface where user-provided descriptions are interpolated into JSON payloads for AI model execution; however, this is standard functionality for generative tools and uses structured data formatting to mitigate accidental command confusion.
Audit Metadata