awesome-web3-security-overview

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly directs the agent to fetch the full resource list from the public GitHub raw URL https://raw.githubusercontent.com/gmh5225/awesome-web3-security/refs/heads/main/README.md, a user-controlled public source that the agent is expected to read and use to drive duplicate checks and categorization decisions, so untrusted content there could influence next actions.