sec-edgar

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

• Third-party content exposure detected (high risk: 0.75). Yes—at runtime the required workflow calls the get_sec_filings tool / sec_edgar_client transport, which fetches SEC public JSON endpoints (e.g., company_tickers.json, submissions/CIK*.json, api/xbrl/companyfacts/CIK*.json) and injects their decoded fields (including free-text like primaryDocDescription) into the agent/tool output that the LLM can read.