anything-to-notebooklm

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests untrusted public content — e.g., arbitrary webpages, 微信公众号 articles via the wexin-read-mcp MCP server, YouTube videos, and WebSearch results (see SKILL.md / README.md) — and passes that content to NotebookLM for reading and generation, exposing the agent to possible indirect prompt injection.