edgartools

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can ingest outsider-authored SEC filing content into the LLM context via methods like filing.text(), filing.markdown(), and filing.to_context()/xbrl.to_llm_context() after fetching a filing from the SEC (public web content authored by the issuer).