finance-ml
Warn
Audited by Snyk on Apr 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to fetch market and instrument data from public third-party sources (e.g., yfinance, financedatabase, alpha_vantage, ccxt) and to use those feeds in the ML-informed trading workflow to generate signals and execute orders, so untrusted public data is ingested and can materially influence actions.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly includes integration with a decentralized exchange (Aster DEX) and a concrete ML-informed trading workflow that lists actionable API calls: get_klines, get_positions, get_balance, and critically create_order(symbol, side, type, quantity, price). Those are direct trading/execution calls (market orders) and the skill references an "aster-trading" skill with MCP tools for Aster DEX. This is not a generic data/analysis tool — it defines functions to place orders and manage positions, i.e., directly move financial assets.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata