Required before calling image_generate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2 through the Hive image service, billed to the user's Hive credits like an LLM call (no API key needed). Teaches the exact call shape, the quality/cost tradeoff (quality="low" is the default and cheapest), reference-image editing, how to show the result to the user with attach_file, and the failure modes (out of credits, model unavailable, moderation).
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a legitimate image-generation guide, but it silently forces any higher quality request down to "low" and does not tell the agent to inform the user, which is a limitation hidden from the user rather than malicious intent.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow ingests no outsider text by default, but the optional `reference_images` parameter accepts arbitrary user-supplied http(s) URLs whose content the image service fetches and conditions on, which the agent did not select from any feed.
aden-hive/hive
c6c2cdc
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.