emergency-news-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls the Grounding API's web_search tool (see monitor_breaking_news and Step 1 grounding_api.search with "breaking stock market news") to fetch public news articles and then reads article.headline and article.content for classification and alerting, which exposes the agent to untrusted third‑party web content.