The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes subprocess.run in several scripts (run.py, setup_environment.py, and __init__.py) to manage its execution environment. This includes creating a Python virtual environment, upgrading pip, and installing necessary dependencies and browser binaries.
[COMMAND_EXECUTION]: A central wrapper script (run.py) uses subprocess.run to invoke the skill's internal logic scripts (e.g., ask_question.py, auth_manager.py) while ensuring they run within the correct virtual environment context.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to retrieve and process text from external Google NotebookLM notebooks. This introduces a potential attack surface where malicious instructions embedded in a user's notebook could influence the agent's behavior. The skill provides instructions for the agent to analyze the retrieved information for completeness but does not implement explicit sanitization of the synthesized responses.

notebooklm