sec-edgar-skill

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests public SEC EDGAR filings via EdgarTools (e.g., get_filings, get_current_filings, Company(...).get_filings(...) and reading filing.text()/filing.items()/filing.markdown()/filing.xbrl()), which are open/public third‑party documents the agent is expected to read and use to drive analysis and decisions—exposing it to untrusted external content that could enable indirect prompt injection.