moonpay-prediction-market

Warn

Audited by Snyk on Mar 25, 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.md workflow and commands (e.g., mp prediction-market market search and mp prediction-market market event retrieve) explicitly pull market data from public, user-generated prediction platforms (Polymarket, Kalshi), which the agent is expected to read and use to make trading decisions, exposing it to untrusted third‑party content that could include injected instructions.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly designed to execute financial transactions: it integrates with blockchain wallets (EVM/Polygon and Solana), requires funding with USDC, and provides concrete commands to buy and sell positions (mp prediction-market position buy / position sell) including wallet, tokenId, price, and size. These are market-order style operations on Polymarket/Kalshi (crypto-backed prediction markets), i.e., direct execution of trades/transfers. This meets the "Direct Financial Execution" criteria.

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
Mar 25, 2026, 04:57 PM
Issues
2