yield-agentkit-moonpay

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md Step 3 and related references) instructs the agent to call the external Yield.xyz AgentKit MCP (e.g., yields_get, yields_get_validators) and to read fields like mechanics.arguments.enter which the agent must interpret to build transactions that are then signed/broadcast via MoonPay, meaning external MCP responses (from yield.xyz) are ingested and can directly influence subsequent tool use and actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's setup instructs the agent to run "npm install -g @moonpay/cli" at runtime, which fetches and executes remote code from the npm registry (e.g. https://registry.npmjs.org/) and is a required dependency for the MoonPay MCP, so this is a runtime external dependency that executes code.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly built to perform on-chain financial operations: it discovers yield opportunities, builds transactions (actions_enter/actions_exit/actions_manage), and uses MoonPay tools for wallet auth, transaction_sign and transaction_send to sign and broadcast transactions. These are specific crypto/blockchain transaction capabilities (wallet signing and broadcasting), not generic tools, so it grants direct financial execution authority.