strategy-memepump-scanner
Warn
Audited by Snyk on Mar 24, 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 repeatedly fetches and ingests public token data (e.g., "Every 10 seconds, fetches MIGRATED pump.fun tokens from OKX Trenches API" and cross-skill calls like
plugin-store memepump token-details,token-dev-info,token-bundle-info) and directly uses that untrusted, user-generated third‑party content to drive signal detection and automated trading decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill runs curl | sh at runtime to install required runtime components (onchainos and plugin-store/strategy), e.g. https://raw.githubusercontent.com/okx/onchainos-skills/main/install.sh, https://raw.githubusercontent.com/okx/plugin-store/main/install.sh, and https://raw.githubusercontent.com/okx/plugin-store/main/install_strategy.sh which fetch and execute remote code and are required dependencies.
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 crypto trades. It contains commands to execute trades (e.g., strategy-memepump-scanner tick / start), an execution pipeline step "try_open_position ← Liquidity check + quote + swap + broadcast", position sizing and slippage parameters (sol_per_trade, slippage_pct, max_sol), automatic buy/sell/TP/SL logic, and integration with a signing wallet (onchainos wallet TEE signing). It is specifically designed to move cryptocurrency (open/close positions, broadcast swaps), not a generic tool. This matches the crypto/blockchain category (wallets, swaps, signing), so it grants direct financial execution authority.
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata