NYC

quicknode-skill

Warn

Audited by Snyk on Feb 16, 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 includes examples and runtimes that fetch and process public, user-generated content—e.g., IPFS gateway retrieval (https://YOUR_GATEWAY.quicknode-ipfs.com/ipfs/{cid}), NFT/asset queries via qn_fetchNFTs and the Solana DAS API (getAssetsByOwner / searchAssets), and Streams/Webhook subscriptions—so the agent would read and act on untrusted third-party data from the open web.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill explicitly exposes blockchain transaction and payment capabilities. It includes crypto-specific APIs and examples for signing and executing operations: x402 pay-per-request RPC demonstrating use of a private key/wallet client and automatic USDC micropayments; a Jupiter Swap API example that performs a swap (swapPost) using a user public key; Hyperliquid endpoints/streams and Info API that reference orders, deposits, withdrawals, and writer_actions (system-level token transfers). These are specific financial/crypto execution primitives (wallet signing, swaps, token transfers), not generic tooling, so it grants direct financial execution authority.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:23 AM