infranodus-orchestrator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls InfraNodus MCP tools that fetch and analyze public web/search data—e.g., analyze_google_search_results, analyze_related_search_queries, search_queries_vs_search_results and generate_seo_report—which ingest untrusted third-party search results and related queries that the agent reads and interprets as part of its workflow.