sentiment-shift

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to call get_daily_summary, get_ticker_sentiment, and search_viewpoints to ingest and analyze blogger viewpoints and public blog/forum content (untrusted user-generated third-party sources), so the agent will read and interpret arbitrary third-party content.