landing-experience-checker

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text when it performs the keyless rendered-page read via firecrawl.py scrape <landing-url> --mobile, because the landing page content at an arbitrary destination URL is not authored by the operating user and is converted into readable markdown that the agent then analyzes for message-match/above-the-fold/form/mobile checks.