app-store-screenshots
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the inference-sh GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to take user-supplied prompts for image and video generation models executed via the belt CLI.
- Ingestion points: User-provided text prompts are interpolated into the
--inputargument ofbelt app runcommands. - Boundary markers: None present; prompts are passed directly within JSON strings in shell commands.
- Capability inventory: The skill is authorized to use the
Bashtool to execute thebeltcommand. - Sanitization: None explicitly defined; the skill relies on the underlying platform's handling of command-line arguments and the AI model's safety filters.
Audit Metadata