develop-data-analysis-dashboard

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

• Third-party content exposure detected (high risk: 1.00). The skill's Data Sources and Workflow sections explicitly require ingesting and "read sources in depth" including "web-sourced data" and instruct persisting web/MCP data to JSON before analysis (see "Data Sources" and "Planning prep" in SKILL.md), which means the agent will fetch and interpret untrusted third-party web content that can influence dashboard planning and tool use.