aicoin-trading

Warn

Audited by Snyk on Apr 30, 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 fetches live market data from third-party APIs (e.g., lib/aicoin-api.mjs calls https://open.aicoin.com and scripts/exchange.mjs uses ccxt to call exchange APIs like ex.fetchTicker, ex.fetchPositions, ex.loadMarkets), and those external responses are read and used by the agent to build previews and to decide/execute orders (see create_order, markets, ticker, positions flows), so untrusted third‑party content can materially influence actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill conditionally runs npm install at runtime (execSync('npm install --omit=dev')), which will fetch and execute external package code (e.g., ccxt) from the npm registry (https://registry.npmjs.org/) and is a required runtime dependency for exchange functionality, so it constitutes a remote-code-executing external dependency.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill is explicitly a trading/order-execution tool for crypto exchanges. It defines commands that directly place market orders (node scripts/exchange.mjs create_order with confirmed=true), close positions (close_position), cancel orders, set leverage/trading params, and targets specific exchanges (OKX, Binance, Bybit, etc.). This is a purpose-built financial execution interface (crypto trading), not a generic tool, so it clearly grants direct financial execution capability. The two-step preview/confirm requirement does not change that it sends real trades when confirmed.

Issues (3)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 30, 2026, 02:27 AM
Issues
3