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 ingests open/public third-party content — e.g., Google News RSS, CoinGecko, Yahoo Finance, Twitter/X via the bird CLI, and SEC EDGAR as described in SKILL.md, HOT_SCANNER.md and implemented in scripts/analyze_stock.py (check_breaking_news, hot_scanner and sentiment modules) — and that untrusted, user-generated content is parsed and directly influences scoring, confidence adjustments, and recommendations (e.g., geopolitical/rumor penalties), enabling indirect prompt-injection risks.