Multi-Agent Architect

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

• Third-party content exposure detected (high risk: 0.90). The skill's CrewAI example explicitly defines a "researcher" agent with tools=[search_tool, scrape_tool] tasked to "Gather comprehensive information" and produce "Comprehensive research findings with sources," which implies fetching and ingesting open/public web content (e.g., arbitrary sites/competitor pages) that the agents will read and interpret.