edgartools

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public SEC EDGAR filings (e.g., get_filings, get_by_accession_number and methods like filing.text(), filing.html(), filing.markdown() and the edgar_filing MCP tool) — all documented in SKILL.md and references/filings.md — which are untrusted third‑party content used to build LLM context and drive agent tools, so those documents could materially influence agent behavior.