aicoin-onchain

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the execution of Node.js scripts (e.g., trade.mjs, swap.mjs, token.mjs) to interact with blockchain networks and the OKX Web3 API.
  • [EXTERNAL_DOWNLOADS]: The skill connects to web3.okx.com for market data and swap routing. It also interacts with various well-known blockchain RPC providers, such as llamarpc.com, binance.org, and polygon-rpc.com, to broadcast transactions and query network state.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external API endpoints (token search results, market information), which represents a theoretical surface for indirect prompt injection if an attacker were to poison on-chain metadata.
  • Ingestion points: Data returned from OKX API calls in scripts/token.mjs, scripts/market.mjs, and scripts/portfolio.mjs.
  • Boundary markers: None explicitly defined for the model, but scripts handle data in structured JSON format.
  • Capability inventory: The skill can perform network operations and local transaction signing using provided private keys.
  • Sanitization: Standard JSON parsing is applied to all API responses before they are presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:47 PM