executive-dashboard-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests arbitrary external data (CSV/Excel files, "Google Sheets links", and JSON/API responses) as part of its workflow—see "Data Input Handling" and "Response Approach: Request the data files or links"—so the agent will read untrusted third-party content that could carry indirect prompt injections.