web3-security-tooling

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Data Source" directs the agent to fetch a public GitHub raw URL (https://raw.githubusercontent.com/gmh5225/awesome-web3-security/refs/heads/main/README.md), which is untrusted, user-managed third‑party content the agent would read and use to decide categorization and tooling, creating a clear avenue for indirect prompt injection.