milan-news-briefing

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

• Third-party content exposure detected (high risk: 0.95). At runtime, src/news_briefing/pipeline.py fetches outsider-authored free text from public web sources (RSS/HTML via fetch_text/fetch_json and web search via fetch_web_search), then parses it into NewsItem.title/summary and includes those strings in the generated Markdown/JSON output (and thus into the agent-visible context when the skill is run).