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, Twitter/X via the bird CLI in the Hot Scanner, CoinGecko and Yahoo Finance endpoints in hot_scanner.py and analyze_stock.py) and uses that untrusted, user-generated or public content to compute sentiment, rumor/impact scores, penalties, and automated recommendations—meaning third-party text can materially influence the agent's decisions and tool behavior.