stock-question-refiner

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires ingesting and citing open/public third-party sources (see "Data Sources" and Phase 6: "Market Sentiment" which lists news and social media such as 雪球 and East Money, and mandates a bibliography with URLs), including user-generated social media content that the agent is expected to read and interpret as part of its workflow, creating a pathway for indirect prompt injection.