notebooklm
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a central wrapper script (
scripts/run.py) to manage its internal environment and route commands to specific automation scripts. - The
run.pyscript employsos.execv()to switch the process context to a local virtual environment. - Security controls include a strict allowed-list of supported scripts (
ALLOWED_SCRIPTS) and a regular expression check for script filenames. - Path resolution checks are performed to ensure script execution cannot escape the designated
scripts/directory. - [CREDENTIALS_SAFE]: The skill manages Google authentication data with robust local security measures.
- Authentication cookies and session state are stored in a dedicated user data directory (
~/.local/share/agentic-awesome-skills/notebooklm). - The skill sets a global
os.umask(0o077)to ensure all files created by the browser or the skill are private by default. - Explicit
chmodcalls restrict sensitive files (state.json,auth_info.json) to0600permissions and directories to0700permissions. - [INDIRECT_PROMPT_INJECTION]: The skill acknowledges the risk of processing untrusted content from the NotebookLM web interface.
- Ingestion points: External data enters the agent context via responses scraped from
notebooklm.google.cominscripts/ask_question.py. - Boundary markers: The skill uses explicit delimiters (
--- BEGIN UNTRUSTED NOTEBOOKLM CONTENT ---) to separate external data from system instructions. - Capability inventory: The skill has the ability to write to private local storage and execute internal scripts via the
run.pywrapper. - Sanitization: External content is serialized as JSON strings and written to private temporary files to prevent it from polluting terminal logs or being accidentally interpreted as commands.
- Human-in-the-loop: Instructions in
SKILL.mdrequire the agent to pause and ask for user confirmation before using metadata (names, descriptions, topics) discovered from a notebook. - [EXTERNAL_DOWNLOADS]: The skill automates the installation of necessary browser binaries during its first-run setup.
- It uses the official
patchrightCLI to install Google Chrome and Chromium binaries, which is a standard procedure for browser automation tools.
Audit Metadata