evm-deployment

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 explicitly instructs interacting with public third-party services—e.g., searching https://chainlist.org/ for RPC endpoints and using Etherscan/Blockscout APIs for contract verification as shown in references/deploy.md and references/examples.md—so the agent is expected to fetch and interpret untrusted external web/API content (explorer responses, RPC endpoints) that can materially change deployment/verification actions.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly for deploying and initializing smart contracts on EVM chains (uses Foundry/forge, RPC configuration, deterministic CREATE2 vs CREATE, contract verification, broadcasting deployment artifacts). It also includes initial setup steps that mint or verify ERC20 token balances, run init scripts to create test streams, and create airdrop/escrow campaign contracts via factories — all actions that require sending signed blockchain transactions and can move or create crypto assets. These are specific crypto/blockchain execution capabilities (not generic tooling), so it grants direct financial execution authority.