3-statement-model

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

• Third-party content exposure detected (high risk: 0.90). The skill's SEC Filings Data Extraction instructions (references/sec-filings.md) explicitly require fetching and parsing public SEC EDGAR filings (e.g., https://www.sec.gov/...), meaning the agent will ingest third‑party public content and use it to populate and drive model-building decisions, which could allow indirect prompt injection.