polymarket

Fail

Audited by Snyk on Feb 19, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The prompt includes examples that directly embed API keys, private keys, and passphrases into code and shows creating/saving credentials, which encourages handling secrets verbatim and risks exfiltration.

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

  • Third-party content exposure detected (high risk: 0.90). This skill directly fetches and processes data from public Polymarket endpoints (e.g., Gamma API at https://gamma-api.polymarket.com, Data API at https://data-api.polymarket.com and the public WebSocket wss://ws-subscriptions-clob.polymarket.com/ws/) — including user-generated comments and public profiles — and the SKILL.md plus example scripts (market_scanner.py, stream_orderbook.py, etc.) show the agent consuming that content to drive research and trading actions, so untrusted third-party content can materially influence behavior.

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


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

  • Direct money access detected (high risk: 1.00). The skill is a purpose-built SDK for trading on Polymarket and managing on-chain funds. It explicitly exposes order placement and cancellation (client.orders.place_order, order_builder.buy(...).build()), authenticated trading using private keys/credentials, and a bridge service for deposits and withdrawals. Examples show using a POLY_PRIVATE_KEY to place orders. These are specific financial execution capabilities (market orders, crypto wallet signing, and fund transfers), not generic tooling.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 19, 2026, 01:04 PM