portfolio-health-check

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly instructs fetching real-time and historical market data via references/data-queries.md (calling ../findata-toolkit-cn/scripts/views_runner.py and tool views such as stock_zh_a_hist which pull from third-party public sources like 东方财富 and optional XUEQIU tokens), so the agent will ingest untrusted public web-sourced data that can materially affect analysis and actions.