wrds

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly downloads and parses external SEC/EDGAR filings (see references/edgar.md "download_10k_text"/"get_filings_from_sec_api" and examples/wrds_connector.py WRDSConnector.get_proxy_text which fetches from WRDS file archives and https://www.sec.gov), so the agent ingests open/public third‑party content and uses that content to drive parsing/analysis and follow‑on actions, creating a clear avenue for indirect prompt injection.