gmx-liquidity
Warn
Audited by Snyk on Mar 31, 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 and interprets live market/pool data from public third‑party endpoints (e.g., sdk.markets.getMarketsInfo(), REST https://arbitrum-api.gmxinfra.io/markets/info and Subsquid GraphQL URLs) to discover pool addresses, balances, and compute execution fees that directly determine contract calls and multicall parameters.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly describes on-chain financial operations for the GMX protocol: depositing/withdrawing/shift of LP (GM) tokens and GLV vault tokens, token approvals, constructing and sending multicall transactions (ExchangeRouter.multicall, GlvRouter.multicall), functions like createDeposit/createWithdrawal/createShift/createGlvDeposit/createGlvWithdrawal, sending native token execution fees (sendWnt/sendTokens), and example walletClient.writeContract calls with concrete contract addresses. These are concrete crypto transaction APIs for moving funds and managing assets on-chain (not generic tooling), so the skill grants direct financial execution capability.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata