strategy-signal-tracker

Fail

Audited by Snyk on Mar 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). The set includes multiple direct raw GitHub shell scripts (curl|sh) — including from a low-reputation personal account (purong-huang-1121) — plus an internal Lark doc link; executing those .sh installers without review is high-risk because they can run arbitrary code, even though one URL points to an official okx repo which is lower risk.

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly polls the public OKX Signal API (POST /api/v6/dex/market/signal/list) every 20s and fetches public token data (price_info, candles, memepump tokenDevInfo/tokenBundleInfo, quote, etc.) and directly uses that untrusted third‑party data to decide and execute trades, so external content can materially influence agent actions.

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 explicitly a trading bot that performs on-chain swaps and broadcasts signed transactions. It describes executing position-sized trades via OKX DEX (swap-instruction), signing transactions (sign_transaction/keypair) and calling /api/v6/dex/pre-transaction/broadcast-transaction to broadcast signed txs, waits for order confirmations, checks/writes balances, and requires an onchainos wallet (TEE signing). It provides commands that perform execution (strategy-signal-tracker tick / start) and details position sizing, slippage, and cost/breakeven calculations. These are specific, primary financial-operation capabilities (placing trades and broadcasting transactions), not generic tools, so this is direct financial execution authority.

Issues (4)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

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
CRITICAL
Analyzed
Mar 17, 2026, 11:22 PM
Issues
4