The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external text prompts and image URLs provided by the user to generate or edit images.
Ingestion points: The prompt and image_url fields within the API request payloads in SKILL.md.
Boundary markers: No explicit delimiters or boundary markers for user-provided prompts are specified in the instructions.
Capability inventory: The skill facilitates network requests (via curl or potential tool use) to the api.acedata.cloud endpoint.
Sanitization: The instructions do not define specific sanitization or validation logic for the content of the prompts or image URLs before they are sent to the API.

flux-image