find-exposed-servers

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests free-text content from passive scanning platforms (e.g., HTTP response bodies/banners and similar fields returned by Shodan/Censys/FOFA via queries, including attacker-controlled web page content), so outsider-authored text can be read into the model’s context without selecting a specific pre-vetted item.