polymarket-bot

Warn

Audited by Snyk on Apr 9, 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 fetches public, user-generated market data from Polymarket (polymarket-data) and performs web research via the Perplexity publisher (see SKILL.md and scripts/agent.py: research_opportunity calling self.seren.research_market and estimate_fair_value), and those third‑party research summaries and market content are directly consumed by the agent to estimate fair value and drive trading decisions.

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

  • Potentially malicious external URL detected (high risk: 0.80). The agent calls Seren publishers at runtime (e.g., via https://api.serendb.com) to fetch Perplexity research (seren.research_market) and then injects that remote research text into the Claude prompt used to estimate fair value, so external content fetched at runtime directly controls the model prompt and is a required 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 live trading agent for Polymarket: it is specifically designed to execute market orders, manage positions, and sign/send transactions. It requires Polymarket API credentials and wallet private keys (POLY_PRIVATE_KEY / WALLET_PRIVATE_KEY, POLY_API_KEY, POLY_PASSPHRASE, POLY_SECRET), uses py-clob-client via DirectClobTrader with local EIP-712 signing, and contains explicit rules for fetching order books, submitting marketable sells/buys, sweeping the book, and running scheduled live execution. This is direct crypto/blockchain and market-order execution capability (not a generic tool), so it grants direct financial execution authority.

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 9, 2026, 12:31 PM
Issues
3