notebooklm-mcp-cli

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the agent’s LLM context via the MCP server’s runtime ingestion of user-supplied web URLs (public web content fetched/scraped at runtime through nlm source add --url ... / research_start --source_type web), which is then used for NotebookLM queries and returned to the agent.