imagegen
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local Python script (
scripts/image_gen.py) that implements image generation logic and is designed to be executed via the command line when requested by the user. - [EXTERNAL_DOWNLOADS]: The CLI workflow performs network requests to the OpenAI API for image generation and processing. These operations target well-known official endpoints.
- [PROMPT_INJECTION]: The skill manages an attack surface for indirect prompt injection by processing user-provided text prompts and images.
- Ingestion points: User-supplied prompts and local image files are ingested as primary inputs for the workflow.
- Boundary markers: The skill utilizes structured templates with explicit sections for 'Constraints' and 'Avoid' to clearly define operational boundaries for the generation process.
- Capability inventory: The skill has the ability to write generated assets to the local filesystem (under
output/imagegen/) and perform outbound network calls via the OpenAI SDK. - Sanitization: The implementation includes a prompt augmentation phase that normalizes and structures user input into a standardized format before external API transmission.
Audit Metadata