finding-arbitrage-opportunities

Warn

Audited by Snyk on Apr 13, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests live public market data from third-party sources (e.g., CoinGecko, CCXT/CEX APIs, and TheGraph Uniswap subgraphs) — see SKILL.md/ARD.md resources and config/settings.yaml — and scripts/price_fetcher.py and opportunity_scanner.py consume that data to drive scans, alerts, and execution decisions, so untrusted external content can materially influence agent behavior.

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

  • Direct money access detected (high risk: 1.00). This skill is explicitly and narrowly focused on cryptocurrency trading/arbitrage (CEX, DEX, cross-chain). It references exchange APIs and CCXT (a trading/exchange library), optional exchange API keys for real-time order-book access, buy/sell recommendations, triangular and cross-chain arbitrage, monitoring with alerts, and an “export opportunities for bot integration” workflow. Those details show the skill is specifically designed for financial trading operations and to be integrated with exchange/trading APIs (i.e., moving crypto/value), not a generic data tool. Therefore it meets the criterion for Direct Financial Execution risk.

Issues (2)

W011
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 13, 2026, 10:54 PM
Issues
2