industry-chain-mapper

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and data instructions (references/data-queries.md and references/methodology.md) explicitly direct running shared scripts that fetch public third‑party data sources (e.g., 东方财富/同花顺/AKShare/国家统计局/company announcements and other web data) which the agent is expected to read and use to drive analysis and decisions, creating a clear path for untrusted external content to influence behavior.