strategy-ranking-sniper

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). These links include raw shell scripts and release endpoints from an unvetted personal GitHub account (plus a cloud doc link) and the skill explicitly instructs curl|sh and installing/running binaries — a high-risk pattern for distributing malware or running arbitrary code.

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses public OKX Onchain OS MCP / onchainos data (e.g., dex-okx-market-token-ranking, dex-okx-market-token-advanced-info, dex-okx-market-token-holder as shown in SKILL.md and engine.py's fetch_* / run_onchainos calls) and directly uses that untrusted, third‑party token/ranking/holder content to drive buy/sell decisions and tool use, so it is exposed to indirect prompt-injection risk.

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 for Solana and includes concrete, specific mechanisms to execute financial transactions: CLI commands that perform buys/sells (tick, start, test-trade, sell, sell-all), configurable budget and per-trade amounts, and explicit Trade Execution APIs (/api/v6/dex/aggregator/swap, /api/v6/dex/pre-transaction/broadcast-transaction). It also uses Solana RPC methods (sendTransaction, getLatestBlockhash, getSignatureStatuses) and onchainos wallet TEE signing for transaction signing. These are direct crypto trade/wallet signing and broadcast capabilities — not generic tooling — so it grants 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, 08:39 PM
Issues
4