aomi-transact

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs embedding secrets in commands (e.g., --private-key 0xYourPrivateKey, --api-key, RPC URL flags) which requires the agent to include secret values verbatim in generated command output, creating an exfiltration risk.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill, by default, uses the remote backend https://api.aomi.dev at runtime to host conversation state and produce agent responses, so this external URL directly controls the agent's prompts/instructions and is a required dependency.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly designed to build, sign, and broadcast on-chain EVM transactions and to perform token swaps and wallet operations. It exposes commands for swapping tokens, sending transactions, signing with a private key (via aomi sign --private-key), EIP-712 typed-data signatures, and specifying an RPC URL to broadcast — i.e., direct crypto/blockchain financial execution capabilities.