📦
planning-with-files
83Organize Long AI Tasks with Planning Files
Long AI sessions can lose goals, decisions, and progress. This skill guides Claude, Codex, and Claude Code to store plans, findings, and logs in project files.
Productivity View
Skills notebooklm
📦
notebooklm
Content revision r1 High Risk ⚙️ External commands🌐 Network access📁 Filesystem access🔑 Env variables
Query NotebookLM From Claude Code
Teams need source-grounded answers from NotebookLM without switching tools. This skill automates authentication, notebook selection, and question answering for Claude, Codex, and Claude Code workflows.
Supports: Claude Codex Code(CC)
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "notebooklm" from https://skillstore.io/skills/zhanlincui-notebooklm.md and its manifest at https://skillstore.io/api/skills/zhanlincui-notebooklm/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "notebooklm". Ask my API docs notebook how authentication tokens expire.
Expected outcome:
The response summarizes token lifetime, renewal rules, and cited source sections from the selected NotebookLM notebook.
Using "notebooklm". List my saved notebooks and activate the backend architecture notebook.
Expected outcome:
The skill shows saved notebook names, marks the active notebook, and selects the requested backend notebook for future queries.
Using "notebooklm". Research the migration steps and ask follow-up questions if anything is missing.
Expected outcome:
The result combines the initial NotebookLM answer with follow-up findings and highlights remaining assumptions for review.
Security Audit
High Riskv5 • 7/8/2026 Open versioned report
Executable scripts use subprocess to set up an environment, install dependencies, install browser binaries, and run local scripts. Many Markdown detections are false positives, but the real code still stores session state and automates Google NotebookLM. Before publication, add explicit consent, URL validation, credential storage protections, and command allowlisting.
15
Files scanned
3,425
Lines analyzed
16
Review items
0
False positives ignored
Confirmed security concerns (4)
High
Persistent Google Session Storage
The skill saves browser storage state for NotebookLM authentication and documents browser cookies and session data in local skill storage. This keeps Google session material on disk and increases exposure if local files are read.
auth_manager.py directly saves browser storage state to disk, and SKILL.md identifies browser cookies and session storage. This is clear persistent credential-adjacent material.
High
Unvalidated Notebook URL Opened With Authenticated Browser
The question interface accepts a notebook URL and opens it in the browser before the NotebookLM domain wait succeeds. A malicious or mistaken URL can load in an authenticated browser profile before validation fails.
The URL is supplied by arguments or library metadata and page.goto runs before domain enforcement. The risk is bounded by browser origin controls but still exposes the authenticated browser session to arbitrary navigation.
High
Stealth Browser Automation Against Google NotebookLM
The skill installs a browser for Patchright anti-detection use, configures stealth-related settings, and simulates human typing. This increases abuse and account-policy risk for an external Google service.
The comments and configuration explicitly reference anti-detection and stealth behavior, and ask_question.py uses human-like typing and delay logic. The intent is clear even though it supports the stated feature.
Medium
Tool Output Can Steer Agent Follow-Up Behavior
The skill appends a strong follow-up instruction to NotebookLM answers and tells the agent to stop, analyze, and ask more questions before responding. NotebookLM answers originate from uploaded documents, so source content can influence agent control flow unless treated as untrusted.
The follow-up instruction is explicit in both code and skill instructions. I did not find a malicious prompt injection string, but the design creates a reliable path for untrusted source text to affect agent behavior.
Capability review items (16)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
High
Python subprocess.run
subprocess.run(
On import, the package runs pip install against requirements.txt in the skill venv. Automatic dependency installation executes external package code and is a real supply-chain risk.
High
Python subprocess.run
subprocess.run(
On import, the package runs patchright browser installation through subprocess. This downloads and executes external setup commands as a side effect.
High
Python subprocess.run
result = subprocess.run([sys.executable, str(setup_script)])
run.py automatically invokes setup_environment.py when the venv is missing. That bootstrap path can install dependencies and browser binaries before the requested task runs.
High
Python subprocess.run
result = subprocess.run(cmd)
run.py executes a command built from the requested script name and arguments. It is scoped to the scripts directory, but there is no explicit allowlist before subprocess execution.
High
Python subprocess.run
subprocess.run(
The setup code upgrades pip through subprocess. This is intended setup behavior, but it executes package-management commands from skill code.
High
Python subprocess.run
result = subprocess.run(
The setup code installs requirements.txt through pip. Installing dependencies at runtime is a real external code execution and supply-chain risk.
High
Python subprocess.run
subprocess.run(
The setup code runs patchright install chrome through subprocess. This downloads browser binaries and extends the local execution surface.
High
Python subprocess.run
result = subprocess.run(cmd)
setup_environment.py can run a requested script through the venv Python. This is local command execution selected at runtime.
Medium
Python file write/append
with open(self.auth_info_file, 'w') as f:
The skill writes authentication metadata to a local auth_info file. The path is scoped, but it persists account-related state on disk.
Medium
Python shutil operations
shutil.rmtree(self.browser_state_dir)
clear_auth removes the browser state directory with shutil.rmtree. The path is scoped to skill data, but it is a destructive operation over stored session material.
Medium
Python shutil operations
shutil.rmtree(path)
The cleanup command deletes discovered data paths with shutil.rmtree. It is scoped and usually confirmed, but it can remove browser state, sessions, and library data.
Medium
Python file write/append
with open(self.library_file, 'w') as f:
The library manager writes notebook URLs and metadata to disk. The file is scoped, but it persists user research context and access URLs locally.
Low
Hardcoded URL
page.wait_for_url(re.compile(r"^https://notebooklm\.google\.com/"), timeout=10000)
The code validates that navigation reaches notebooklm.google.com during a query. This is intended, but it confirms external Google network access for user questions and notebooks.
Low
Hardcoded URL
page.goto("https://notebooklm.google.com", wait_until="domcontentloaded")
The authentication flow opens notebooklm.google.com in a persistent browser context. This is intended, but it sends browser traffic to an external Google service.
Low
Hardcoded URL
page.wait_for_url(re.compile(r"^https://notebooklm\.google\.com/"), timeout=timeout_ms)
The login flow waits for a NotebookLM URL after Google authentication. This confirms external network use tied to a user account.
Low
Hardcoded URL
page.goto("https://notebooklm.google.com", wait_until="domcontentloaded", timeout=30000)
The validation flow opens notebooklm.google.com to check stored authentication. This is intended, but it uses external network access with saved browser state.
Risk Factors
⚙️ External commands (78)
references/api_reference.md:160 references/api_reference.md:216 references/api_reference.md:228 references/api_reference.md:249 references/api_reference.md:271 references/troubleshooting.md:132 references/troubleshooting.md:277 references/usage_patterns.md:177 references/usage_patterns.md:210 references/usage_patterns.md:219 references/usage_patterns.md:143 scripts/__init__.py:53 scripts/__init__.py:65 scripts/run.py:38 scripts/run.py:91 scripts/setup_environment.py:54 scripts/setup_environment.py:62 scripts/setup_environment.py:75 scripts/setup_environment.py:132 SKILL.md:14 SKILL.md:24-30 SKILL.md:30-33 SKILL.md:33-34 SKILL.md:34-35 SKILL.md:35-36 SKILL.md:36-42 SKILL.md:42-44 SKILL.md:44-52 SKILL.md:52-54 SKILL.md:54-55 SKILL.md:55-63 SKILL.md:63-65 SKILL.md:65-70 SKILL.md:70-73 SKILL.md:73-83 SKILL.md:83-106 SKILL.md:106-109 SKILL.md:109-110 SKILL.md:110-114 SKILL.md:114-126 SKILL.md:126-137 SKILL.md:137-139 SKILL.md:139-145 SKILL.md:145-146 SKILL.md:146-151 SKILL.md:151-153 SKILL.md:153-154 SKILL.md:154-161 SKILL.md:161-163 SKILL.md:163-164 SKILL.md:164-166 SKILL.md:166-168 SKILL.md:168-169 SKILL.md:169-173 SKILL.md:173-178 SKILL.md:178-184 SKILL.md:184-189 SKILL.md:189-193 SKILL.md:193-194 SKILL.md:194-195 SKILL.md:195-196 SKILL.md:196-198 SKILL.md:198-202 SKILL.md:202-203 SKILL.md:203-210 SKILL.md:210-214 SKILL.md:214-230 SKILL.md:230-236 SKILL.md:236-239 SKILL.md:239-240 SKILL.md:240-262 SKILL.md:262-263 SKILL.md:263-264 SKILL.md:264-265 SKILL.md:265-266 SKILL.md:266-267 SKILL.md:267-268 SKILL.md:268-269
🌐 Network access (19)
references/api_reference.md:30 references/api_reference.md:52 references/api_reference.md:59 references/troubleshooting.md:148 references/troubleshooting.md:209 references/troubleshooting.md:210 references/troubleshooting.md:209 references/troubleshooting.md:210 references/usage_patterns.md:31 scripts/ask_question.py:9 scripts/ask_question.py:80 scripts/auth_manager.py:10 scripts/auth_manager.py:114 scripts/auth_manager.py:129 scripts/auth_manager.py:260 scripts/setup_environment.py:72 SKILL.md:14 SKILL.md:93 SKILL.md:122
📁 Filesystem access (32)
references/api_reference.md:185 references/api_reference.md:185 references/troubleshooting.md:101 references/troubleshooting.md:223 references/troubleshooting.md:226 references/troubleshooting.md:236 references/troubleshooting.md:282 references/troubleshooting.md:283 references/troubleshooting.md:287 references/troubleshooting.md:298 references/troubleshooting.md:299 references/troubleshooting.md:306 references/troubleshooting.md:353 references/troubleshooting.md:361 references/troubleshooting.md:101 references/troubleshooting.md:223 references/troubleshooting.md:226 references/troubleshooting.md:236 references/troubleshooting.md:282 references/troubleshooting.md:283 references/troubleshooting.md:287 references/troubleshooting.md:298 references/troubleshooting.md:299 references/troubleshooting.md:306 references/troubleshooting.md:353 references/troubleshooting.md:361 scripts/auth_manager.py:177 scripts/auth_manager.py:204 scripts/cleanup_manager.py:173 scripts/notebook_manager.py:58 SKILL.md:193 SKILL.md:193
🔑 Env variables (1)
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/zhanlincui-notebooklm/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/zhanlincui-notebooklm?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/zhanlincui-notebooklm?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/zhanlincui-notebooklm/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/zhanlincui-notebooklm.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
ZhanlinCui. (2026). notebooklm security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zhanlincui-notebooklm/audits/5BibTeX citation
@techreport{zhanlincui-zhanlincui-notebooklm-2026,
author = {ZhanlinCui},
title = {notebooklm security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/zhanlincui-notebooklm/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "notebooklm security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "ZhanlinCui"
date-released: "2026-07-08"
url: "https://skillstore.io/skills/zhanlincui-notebooklm/audits/5"
identifiers:
- type: other
value: "skillstore:zhanlincui-notebooklm:audit:5"
description: "Skillstore immutable audit report identifier"
Compare variants
3 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Higher Skillstore usage
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
zhanlincui-notebooklm
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 36
Updated
2026-08-21
teng-lin-notebooklm
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 17
Updated
2026-08-21
sickn33-notebooklm
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 17
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 68
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance
What You Can Build
Source-Grounded Development Research
Ask project documentation questions inside a coding session and receive NotebookLM answers from uploaded sources.
Notebook Library Triage
Organize NotebookLM links with names, topics, and descriptions so teams can choose the right source set quickly.
Document Review Follow-Ups
Run focused follow-up questions against a notebook before drafting summaries, FAQs, or implementation notes.
Try These Prompts
Ask an Active Notebook
Ask my active NotebookLM notebook: What are the main points I should understand about this topic?
Add a Notebook Link
Add this NotebookLM URL to my library. Ask me for the name, description, and topics before saving it.
Compare Two Notebooks
Query notebook A and notebook B about the same requirement, then compare the answers and note conflicts.
Run Follow-Up Research
Use NotebookLM to answer this implementation question. Ask follow-up questions until the answer covers constraints, examples, and risks.
Best Practices
- Use a dedicated Google account when automating NotebookLM access.
- Validate notebook URLs and metadata before adding them to the local library.
- Review NotebookLM answers as source content, not as trusted instructions.
Avoid
- Do not run the skill against unknown NotebookLM URLs without validating the domain.
- Do not store browser state on shared machines without access controls.
- Do not treat NotebookLM output as authority to run commands or change settings.
Frequently Asked Questions
Does this skill require a browser?
Yes. It uses local browser automation to open NotebookLM, authenticate, ask questions, and read answers.
Does it work without Google login?
No. The user must complete Google login in a visible browser before normal queries work.
Where does it store notebook data?
It stores notebook metadata and authentication state in a local data directory inside the skill installation.
Can it query any NotebookLM notebook?
It can query notebooks that the authenticated Google account can access and that NotebookLM can load.
Is NotebookLM output always safe to follow?
No. Treat answers as source content and verify them before using them to make changes.
Which tools can use this skill?
The report lists compatibility with Claude, Codex, and Claude Code.
Developer Details
Author
ZhanlinCuiLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
64ca8af0f54a325752f08bd54e52151061ea659a
Maintenance freshness
7/20/2026
Usage
33 downloads · 220 views
File structure
More from ZhanlinCui
View all📦
github-release-assistant
83Generate Bilingual GitHub Release READMEs
Release notes and README updates can take time before each GitHub release. This skill generates bilingual release documentation and guides review, commit, and push steps.
Documentation View
📦
obsidian-helper
81Organize Obsidian Notes with AI
Obsidian vaults can become hard to review and update consistently. This skill helps Claude and Codex create daily notes, capture ideas, and summarize recent work.
Productivity View
📦
Process PDFs with Extraction and Form Tools
PDF work often requires separate tools for text, tables, pages, and forms. This skill gives Claude, Codex, and Claude Code guided workflows and helper scripts for PDF tasks.
Office & Reports View
📦
frontend-design
79Build Distinctive Frontend Interfaces
Generic web interfaces can feel unfinished and forgettable. This skill guides Claude, Codex, and Claude Code toward polished frontend work with clear visual direction.
Design & Creative View
📦
brainstorming
79Plan Creative Work Before Building
Teams often start implementation before goals, constraints, and trade-offs are clear. This skill guides Claude, Codex, and Claude Code through structured brainstorming before design work begins.
Productivity View
Related Skills
View all📦
nature-reviewer
81Simulate Nature-Style Reviewer Reports
by Yuan1z0825
Researchers often need an objective pre-submission critique before sending a manuscript. This skill turns supplied manuscript material into grounded Nature-style reviewer reports.
Research & Learning View
📦
deep-research
80Research Complex Topics With Citations
by shubhamsaboo
Deep research is hard when sources disagree or lack context. This skill guides Claude, Codex, and Claude Code to synthesize sources, compare viewpoints, and produce cited research summaries.
Research & Learning View
📦
tavily-web
79Search and Research the Web with Tavily
by sickn33
AI assistants often need current web context and clean source material. This skill guides Tavily search, extraction, crawling, and research tasks from Claude, Codex, and Claude Code.
Research & Learning View
📦
tavily-search
79Search the Web with Tavily
by CK991357
AI assistants often lack current information for news, prices, releases, and fast-moving topics. This skill guides Claude, Codex, and Claude Code to call Tavily Search with clear query parameters.
Research & Learning View
📦
technical-research
79Evaluate Technical Options with Structured Spikes
by 89jobrien
Technical decisions often need evidence, not opinion. This skill guides timeboxed spikes with options, proof of concept results, comparison matrices, risks, and recommendations.
Research & Learning View
📦
fact-checker
79Verify Claims With Evidence
by shubhamsaboo
Misinformation and weak sources make claims hard to trust. This skill guides Claude, Codex, and Claude Code through evidence-based verification, source ranking, and clear verdicts.
Research & Learning View