wallet

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs decrypting a keystore with a command that prints the private key (piped to awk) and to use it for scripts, which requires the agent to handle and output the secret value verbatim.

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

• Direct money access detected (high risk: 1.00). The skill explicitly provides blockchain wallet and transaction tooling: it requires and manages an agent wallet keystore (~/.monskills/keystore), includes concrete commands to create a wallet (cast wallet new), decrypt private keys for scripts (cast wallet decrypt-keystore ... | awk ...), instructs proposing and submitting transactions via a Safe multisig (propose.sh/propose.mjs) and directs users to fund the wallet. Those are specific crypto wallet/transaction operations (signing, key management, proposing/sending transactions), which constitute Direct Financial Execution capability.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly instructs the agent to create and manage a local keystore (~/.monskills/keystore), run wallet-generation commands, and decrypt private keys (using an empty/unsafe password) to expose them for scripts, which modifies the agent's filesystem and bypasses key security controls.