product-ai-remake

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1 and the references/research-template.md explicitly require researching 50 products "国内外不限" and collecting product names/URLs using external research tools (Perplexity, Google Deep Research, etc.), which requires fetching and interpreting untrusted public web pages whose content will directly drive selection and subsequent actions.