hive-test

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly uses external search and scraping tools (see mcp_servers.json / tool_names = "web_search,web_scrape" and the "research" node examples where the agent calls web_search/web_scrape and ingests "research_results"), so it fetches and interprets untrusted public web content as part of its workflow, enabling indirect prompt injection risk.