space-image-studio
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
scripts/generate_image.py) using a shell command to generate images based on constructed prompts. The command uses variables for output paths and aspect ratios that are determined during the workflow. - [EXTERNAL_DOWNLOADS]: The
generate_image.pyscript makes outbound HTTP POST requests to the LabNana API (api.labnana.com) and Google's Gemini API (generativelanguage.googleapis.com) to transmit generation prompts and download the resulting image data. - [DATA_EXPOSURE]: The skill accesses a local configuration file (
.labnana.env) to retrieve the API key required for image generation. This is a standard practice for managing credentials in local tools, and the instructions explicitly warn the agent not to reveal these keys in the conversation.
Audit Metadata