Agent Workflow Builder

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md (Workflow 3: Build Multi-Agent System and the Implement Agent Loop section) explicitly shows an agent using tools named "web_search" and "read_document" and appending tool results into the agent's message loop for synthesis/decision-making, which indicates the agent will fetch and interpret open/public third-party content that can influence subsequent tool use and actions.