monad

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes an explicit command that captures a freshly printed private key and injects it as a --private-key CLI argument (cast wallet import ... --private-key $(...)), which instructs embedding a secret value verbatim into a command and therefore risks secret exposure/exfiltration.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). Most URLs are legitimate project endpoints and official services, but the raw GitHub installer script (https://raw.githubusercontent.com/category-labs/foundry/monad/foundryup/install) is high-risk because it is a remote install script commonly used with curl | bash, which can be used to deliver malware.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime install command that fetches and immediately executes a remote installer script via curl | bash (https://raw.githubusercontent.com/category-labs/foundry/monad/foundryup/install), which downloads and runs remote code required by the skill.

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

• Direct money access detected (high risk: 1.00). The document contains specific, blockchain-related APIs and code that perform on-chain value transfers and transaction submissions (e.g., Solidity delegate with msg.value, viem walletClient.sendTransaction with value/encodeFunctionData, and an example using walletClient.signAuthorization + sendTransaction). These are explicit crypto transaction primitives/wallet interactions that can move funds or perform staking operations — i.e., direct financial execution.