ai-product-photography

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation guides hosted on GitHub (raw.githubusercontent.com/inference-sh/...). This is a standard and neutral reference to a well-known service for project configuration and instructions.
  • [COMMAND_EXECUTION]: Utilizes the belt CLI tool via the Bash tool to interact with remote AI model APIs. The skill demonstrates authenticating (belt login) and running specialized inference applications (belt app run) for image generation and post-processing tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill structure defines a framework for ingesting user-provided descriptions and transforming them into prompts for AI models.
  • Ingestion points: Product descriptions and style requirements are provided by the user to be used as parameters in belt commands.
  • Boundary markers: Prompts are encapsulated within JSON objects passed to the command-line interface, providing a clear separation between instructions and data.
  • Capability inventory: The skill utilizes the Bash tool to execute the belt command and uses shell redirection to save JSON output to the file system.
  • Sanitization: Input sanitization is managed by the underlying CLI and the external AI service provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:25 AM