The Agent Skills Directory

[SAFE]: The skill performs expected network operations to https://api.ideogram.ai, which is a well-known service for the described image processing tasks.
[SAFE]: Credential management follows best practices by retrieving the API key from environment variables (process.env.IDEOGRAM_API_KEY).
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts which are then sent to an external AI service. This is an inherent part of the image generation workflow.
Ingestion points: prompt parameter in editImage, remixImage, and upscaleImage functions within SKILL.md.
Boundary markers: None provided.
Capability inventory: Performs network requests (fetch) and file system operations (readFileSync, writeFileSync).
Sanitization: No explicit sanitization of input prompts is performed before transmission.

ideogram-core-workflow-b