dcf-model

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly instructs fetching data from "the web" and public sources (Step 1: "Fetch data from MCP servers, user provided data, and the web" and "Web Search/Fetch — Current prices, beta, debt and cash" / "SEC EDGAR filings" in Workflow Integration), meaning it ingests open/public third-party content that can directly influence model assumptions and subsequent actions.