mm

Warn

Audited by Snyk on Feb 20, 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 explicitly connects to public prediction market platforms (Polymarket/Kalshi) — e.g., SKILL.md states “Fair value computed from orderbook” and index.ts calls createFeedManager/createMMStrategy with a marketId/tokenId — so it ingests live, user-generated orderbook/market data that directly drives quoting and execution decisions.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly a market-making/trading tool for prediction markets (Polymarket, Kalshi). It defines commands and an API to start/stop market makers, place and cancel maker orders ("Quotes placed as post-only maker orders"), manage order size/inventory, and auto-halt based on realized P&L. The API examples show creating a strategy with execution and registering/starting bots, implying direct order execution on markets. This is a specific financial-execution capability (placing/canceling orders / managing positions), not a generic tool.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:52 PM