lovstudio-image-creator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Runtime path gen_image.py: the required workflow passes user-supplied prompt directly into client.models.generate_content(..., contents=[prompt]) (and prints any returned part.text) to generate images via ZenMux/Gemini, meaning outsider-authored free text is ingested by the model without selecting a specific trusted item first.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The HTML template loads and requires remote JavaScript from CDNs (e.g., https://cdn.jsdelivr.net/npm/react@19/umd/react.production.min.js) which will be fetched and executed by the renderer (Playwright) at runtime, so these external URLs execute remote code that the skill depends on.