app-store-screenshots
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation and installation steps hosted on the official GitHub repository for inference-sh. These resources are used to set up the necessary CLI tools for the skill's primary function.
- [COMMAND_EXECUTION]: Leverages the
beltCLI tool to run remote AI models (such as Flux and Veo) for image and video generation. This execution is performed within the scope of the skill's stated purpose of creating marketing materials. - [DATA_EXFILTRATION]: Mentions the
belt logincommand, which is the standard procedure for authenticating the CLI tool with the inference.sh platform to enable remote task execution. - [PROMPT_INJECTION]: Identifies a surface for indirect prompt injection, as the skill constructs AI model prompts based on user-provided application descriptions.
- Ingestion points: Input parameters for the
belt app runcommands described inSKILL.md. - Boundary markers: None explicitly defined in the provided command templates.
- Capability inventory: Remote image and video generation via the
beltCLI tool. - Sanitization: No explicit sanitization or filtering of user-provided content is mentioned in the documentation.
Audit Metadata