ahooks

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

• Third-party content exposure detected (high risk: 0.90). The skill's examples and hooks clearly consume untrusted public content — e.g., fetch('https://api.example.com/data'), useWebSocket('wss://api.example.com/chat') and useExternal('https://cdn.jsdelivr.net/...') — which load/parse or even execute third‑party data/assets that the agent would read or act on.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes runtime dynamic script loading via useExternal that injects and executes third‑party JavaScript (e.g., https://cdn.jsdelivr.net/npm/chart.js and https://external-library.com/lib.js), which is fetched at runtime and used as a required dependency to run remote code.