monskill

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

• Potentially malicious external URL detected (high risk: 0.90). The tooling-and-infra skill explicitly instructs agents to fetch external Markdown at runtime (e.g. https://docs.monad.xyz/tooling-and-infra/analytics.md), which will be read into the agent's context and thus can directly control prompts/answers.

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

• Direct money access detected (high risk: 1.00). The skill explicitly provides agent wallet management, Safe multisig creation, deploying smart contracts and performing on-chain actions, and proposing transactions to a Safe Transaction Service with EIP-712 signatures. These are specific crypto/blockchain transaction and signing capabilities (direct financial execution), not generic tooling.