The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the notebooklm-mcp-cli package from PyPI or via the uv tool. This is the official distribution channel for the integration tool provided by the skill author.- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute configuration and authentication commands, such as nlm login for browser-based OAuth and nlm setup to register the MCP server with the local agent configuration. These are standard operations for the tool's functionality.- [DATA_EXFILTRATION]: The skill's primary function involves uploading local documents, text snippets, and codebase summaries to Google's NotebookLM servers for processing. This data transit is intended and documented as part of the RAG (Retrieval-Augmented Generation) workflow.- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection (Category 8) due to its processing of untrusted external content from URLs and automated research tasks.
Ingestion points: External data enters the context via source_add (URLs) and research_import (web and Drive discovery results).
Boundary markers: The skill relies on NotebookLM's internal grounding and the agent's native guardrails; no specific delimiters are added by the skill instructions.
Capability inventory: The agent has access to powerful tools like Bash, Write, and Edit, which could be targeted by instructions hidden in source material.
Sanitization: Content is passed directly to the RAG engine without additional client-side sanitization beyond standard platform protections.

notebooklm