writing-staffing

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

• Third-party content exposure detected (high risk: 0.90). The resources/researchers.md explicitly instructs dispatching the base @web-researcher "for web research" and states researchers produce reports "with trade-off analysis and source URLs," indicating the agent will fetch and read open/public web content (craft references, world facts, social/community sources) that can influence orchestrator decisions.