alterlab-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., company.get_filings(), get_by_accession_number(), filing.html()/text()/markdown(), filing.open()) and the SKILL.md / references/ai-integration.md instructs exporting filings to markdown and using .to_context()/.to_llm_context() for LLM analysis, meaning arbitrary third-party filing content could be read and influence agent decisions or tool use.