yield-optimization

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and scripts (e.g., ./scripts/find-yields.sh and ./scripts/get-yield-info.sh) explicitly fetch yield schemas and data from yield.xyz / its public API/dashboard, and those remote schemas and returned unsignedTransaction JSON are read and used to build, sign, and broadcast transactions—meaning untrusted third‑party content can directly influence tool use and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires cloning and installing https://github.com/stakekit/yield-agent (or installing via npx), and that remote repository's shell scripts are executed at runtime to build/sign transactions (additionally the runtime fetches yield schemas from https://dashboard.yield.xyz), so external content is fetched and executed and directly controls the agent's behavior.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly designed for on-chain financial operations and contains direct transaction- and payment-related commands. It builds deposit/withdrawal transactions and uses MoonPay CLI commands to sign and broadcast them (mp transaction sign, mp transaction send). It also includes explicit fiat-to-crypto and cross-chain movement capabilities (mp buy, mp token bridge, mp virtual-account create / onramp / offramp, mp virtual-account bank-account add). These are specific payment/crypto operations whose primary purpose is moving funds, so this skill grants direct financial execution authority.