notebooklm-cli

WarnAudited by ClawScan on May 10, 2026.

Overview

The skill fits its NotebookLM purpose, but it relies on an unprovided CLI that extracts Chrome session cookies and can change NotebookLM content, so it needs careful review before use.

Before installing or using this skill, verify exactly which nlm CLI it expects and where it comes from. Use a dedicated Google/Chrome profile if possible, understand how cookies and auth profiles are stored, and do not let the agent run delete, sync, import, or batch --confirm commands unless you have reviewed the target notebook IDs.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If the external CLI is not trusted or is over-scoped, it could access the user's Google NotebookLM session and Drive-linked NotebookLM sources under that browser profile.

Why it was flagged

Browser session cookies are high-impact Google account credentials; the artifacts do not bound what cookies are read, where they are stored, or declare a primary credential.

Skill content
`nlm login` ... Launches Chrome, navigates to NotebookLM, and extracts session cookies. Requires Google Chrome installed.
Recommendation

Only use a verified nlm CLI from a trusted source, prefer a dedicated Chrome/Google profile, inspect how credentials are stored, and remove saved profiles when finished.

What this means

Users may need to obtain and run an unreviewed external binary that handles browser cookies and modifies NotebookLM data.

Why it was flagged

The supplied artifacts do not provide or identify the nlm executable even though the documentation tells users to run it for cookie-based authentication and account operations.

Skill content
Source: unknown; Homepage: none ... No install spec — this is an instruction-only skill. ... No code files present
Recommendation

Require a clear upstream source, pinned install instructions, declared required binaries, and reviewable authentication behavior before trusting this skill.

What this means

Mistaken commands could delete notebooks or artifacts, sync Drive sources, or change cloud-side NotebookLM state.

Why it was flagged

The CLI can mutate or delete NotebookLM cloud data. This is purpose-aligned and uses confirmation flags, but the agent should not run these commands without explicit user intent.

Skill content
`nlm notebook delete <notebook-id> --confirm`; `nlm source sync <notebook-id> --confirm`; `nlm studio delete <notebook-id> <artifact-id> --confirm`
Recommendation

Review notebook IDs and operation type before running any --confirm command, especially delete, sync, import, or batch-generation workflows.

What this means

Generated summaries, quizzes, or reports may reflect inaccurate or malicious source content, and selected private documents may become part of a persistent NotebookLM notebook.

Why it was flagged

Imported web or Drive sources become NotebookLM context for chat and generated outputs, so untrusted or sensitive sources can influence later results.

Skill content
Querying sources via chat ... Researching and importing new sources automatically
Recommendation

Vet sources before importing, avoid adding highly sensitive documents unless appropriate for NotebookLM, and review generated outputs before relying on them.