email-finder

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and parses arbitrary public web content (fetch_page used by scrape_website to GET https://{domain}/ pages and search_for_emails fetching Google/hunter.io directory/search pages) and then interprets that untrusted, user-generated content to extract and act on email data, exposing the agent to potential indirect prompt injection.