gpt-image-2-prompt
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is text transformation and prompt construction. It uses a series of markdown templates and guides to help the agent build effective prompts for image models.
- [EXTERNAL_DOWNLOADS]: All external URLs referenced in the skill point to legitimate documentation, official GitHub repositories (e.g., OpenAI Cookbook), or well-known industry blogs. These are used for informational purposes and to cite the source of the prompt engineering logic.
- [COMMAND_EXECUTION]: The skill provides examples of API calls in Python and Midjourney command syntax. These are presented as documentation for the user and are not executed by the skill itself.
- [PROMPT_INJECTION]: There are no patterns suggesting attempts to bypass safety filters or override agent behavior. The instructions focus on improving the clarity and detail of image generation requests.
- [DATA_EXFILTRATION]: No network operations, sensitive file access, or credential harvesting patterns were detected. The skill operates entirely on the provided user input and local reference files.
Audit Metadata