The Agent Skills Directory

[SAFE]: The skill provides standard functionality for interacting with OpenAI's DALL-E 3 and DALL-E 2 APIs for image generation and editing.
[SAFE]: Sensitive credentials (API keys) are managed through environment variables, which is the recommended security practice for agent-based workflows.
[EXTERNAL_DOWNLOADS]: The skill utilizes well-known and reputable Python packages including openai, python-dotenv, Pillow (PIL), and numpy to handle API communication and image processing.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts as inputs to the image generation functions. While this represents a data ingestion surface, the risk is negligible as the output is a binary image file, and the underlying service (OpenAI) maintains its own safety filters for prompt processing.

dalle-api