midjourney-v8-prompt
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to transform user-provided natural language into formatted image prompts for Midjourney, GPT-image-2, and Gemini 3 Pro Image. Analysis of the 10 files shows no evidence of malicious intent or dangerous capabilities.
- [EXTERNAL_DOWNLOADS]: The skill contains multiple references to external documentation and industry guides (e.g., Midjourney official docs, blakecrosley.com, artprompthq.com). These are provided as informational resources for the user and are not used for automated downloads or runtime execution.
- [COMMAND_EXECUTION]: There are no shell commands or system-level operations initiated by the skill. It explicitly states that it only produces text and that users must manually copy and paste the output into external platforms like Discord.
- [DATA_EXFILTRATION]: No sensitive file paths, environment variables, or credentials are accessed. The skill processes user input locally within the conversational context to build the prompts.
- [PROMPT_INJECTION]: The instructions are focused on guiding the user through a structured workflow. There are no attempts to override safety filters or manipulate the underlying agent's core instructions.
Audit Metadata