stock-analysis
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly performs WebSearch for each stock (SKILL.md Step 3) and its data script (references/stock_data_fetcher.py search_news) ingests third‑party news via Tavily/SerpAPI or Claude WebSearch fallback, and those news items are used in STEP 4 to influence scoring and buy/sell decisions — so untrusted web content can materially affect agent actions.
Audit Metadata