openocean

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches data from the OpenOcean API (a third-party DEX aggregator service), which can return token metadata, quotes, and messages containing free text that the agent processes.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes runtime API calls to open-api.openocean.finance and pro-openapi.debank.com for quotes and token data under common/reputable third-party provenance.

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

• Direct money access detected (high risk: 1.00). The skill documentation explicitly includes functionality for executing cryptocurrency token swaps via the OpenOcean DEX aggregator (openocean_swap), managing ERC20 token approvals, and interacting with blockchain wallets. This represents direct financial execution authority (Crypto/Blockchain Swaps/Signing).