ai-product-photography
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches installation guidelines and documentation from the inference-sh GitHub repository.
- [COMMAND_EXECUTION]: Executes shell commands via the
beltCLI tool to interact with the inference platform for image generation and processing. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate image prompts, which creates a potential surface for indirect prompt injection.
- Ingestion points: User input is interpolated into the
--inputargument ofbelt app runcommands within shell scripts and documentation examples. - Boundary markers: User prompts are encapsulated within JSON strings passed to the CLI.
- Capability inventory: The skill utilizes the
Bashtool, restricted to commands starting withbelt. - Sanitization: No explicit sanitization or filtering of prompt text is performed before it is passed to the underlying AI models.
Audit Metadata