Agent Workflow Builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's Workflow 3 explicitly defines a "researcher" agent with tools like [web_search, read_document] that require fetching and synthesizing content from public/untrusted web pages or documents (Build Multi-Agent System section), meaning third-party content would be read and could materially influence agent decisions and tool use.