alphaear-predictor

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs agents to call external search/news tools (e.g., web_search, fetch_news_content in scripts/prompts/fin_agent.py and news_toolkit/search_toolkit in scripts/prompts/trend_agent.py) and passes the resulting public/news text into the forecasting/adjustment workflow (news_context/news_text consumed by PROMPTS.md and KronosPredictorUtility), meaning it ingests untrusted third‑party web/user-generated content that the agent reads and uses—exposing it to indirect prompt injection.