restaurant-competitors

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses runtime web search to fetch “best [cuisine] in [city]/[neighborhood]” and “restaurants near [subject address]”, then ingests competitor details like ratings/reviews and social/website content into the LLM context—i.e., public web content and outsider-authored review text.