margin-risk-monitor

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

• Third-party content exposure detected (high risk: 0.90). Yes — the skill's required workflow and data acquisition steps (see SKILL.md "第二步：获取数据（按需）" and references/data-queries.md) instruct running shared scripts that fetch market data from third‑party public sources (e.g., 东方财富网 and 上海/深圳交易所 views via ../findata-toolkit-cn), which the agent ingests and uses to drive analysis and next actions, exposing it to untrusted third‑party content that could carry indirect prompt injection.