create-chatgpt-mockup

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow reads the provided --thread <path> JSON (including outsider-authored messages[].text / composer.text free text) and injects it into the generated HTML that Playwright loads into the page context (via render.js → generate.js → screenshot.js), so arbitrary outsider text can become LLM-readable prose/markup at runtime.