domain-discovery

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs web searches (search_official_domain) and fetches/inspects public website homepages and metadata (check_common_tlds and validate_domain) and uses those untrusted third-party pages and search results to decide and validate the primary domain, exposing the agent to potential indirect prompt injection via arbitrary web content.