frame-creative-voltage

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

• Third-party content exposure detected (high risk: 0.85). This skill’s runtime LLM context is fed by the user-provided free-text inputs (display_lines, script, meta, caption) that are not authored by the operating user (outsider content), and those strings are rendered into the HTML/CSS/SVG (readable text) via the template’s input schema.