stock-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses open/public third-party content (e.g., Google News RSS in check_breaking_news in scripts/analyze_stock.py and HOT_SCANNER.md, Twitter/X via the bird CLI in hot_scanner.py, Yahoo Finance and CoinGecko endpoints, and SEC EDGAR via edgartools), and it uses that untrusted/user-generated news and social media content to modify scores, apply geopolitical/risk penalties, and drive recommendations and scanner outputs—so external content can materially influence agent decisions.