crypto-research
Warn
Audited by Snyk on Mar 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly calls CoinMarketCap MCP endpoints (e.g., mcp.coinmarketcap.com via functions like search_cryptos, get_crypto_info, get_crypto_latest_news) to ingest public third‑party data (news, project descriptions, social links) which the agent is expected to read and use to drive its analysis and recommendations.
Audit Metadata