Skills/PyPI/notebooklm-enterprise-mcp

notebooklm-enterprise-mcp@1.0.8

CAUTION· install only

Publisher claims: "Unified CLI and MCP server for Google NotebookLM (Enterprise + Personal)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher robiton · publishing for 222 daysInstalls 117Last detonated 28 h ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
NOTEBOOKLM_CSRF_TOKENNOTEBOOKLM_OAUTH_CLIENT_IDNOTEBOOKLM_OAUTH_CLIENT_SECRETNOTEBOOKLM_OAUTH_SERVER_URL or --oauth-client-id / --oauth-client-secret / --oauth-server-urlConfiguration, not credentials: NLM_BROWSER, NLM_NO_COLOR, NLM_OUTPUT_FORMAT, NLM_PROFILE, NOTEBOOKLM_BASE_URL, NOTEBOOKLM_BL, NOTEBOOKLM_COOKIES, NOTEBOOKLM_ENDPOINT_LOCATION, NOTEBOOKLM_HL, NOTEBOOKLM_LOCATION, NOTEBOOKLM_MCP_CLI_PATH, NOTEBOOKLM_MCP_DEBUG, NOTEBOOKLM_MCP_HOST, NOTEBOOKLM_MCP_PATH, NOTEBOOKLM_MCP_PORT, NOTEBOOKLM_MCP_STATELESS, NOTEBOOKLM_MCP_TRANSPORT, NOTEBOOKLM_MODE, NOTEBOOKLM_PROJECT_ID, NOTEBOOKLM_QUERY_TIMEOUT, NOTEBOOKLM_SESSION_ID
Where it talks to
no vendor host named in the codeAlso google.com, youtube.com, example1.com, example2.com, evil.com, a.com, b.com, ft.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names google.com, youtube.com, example1.com, example2.com, evil.com, a.com, b.com, ft.com as well as its own vendor. The guard injects NOTEBOOKLM_CSRF_TOKEN, NOTEBOOKLM_OAUTH_CLIENT_ID, NOTEBOOKLM_OAUTH_CLIENT_SECRET, NOTEBOOKLM_OAUTH_SERVER_URL only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx notebooklm-enterprise-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/cli/commands/setup.py:459 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:441 · Collapsed <details> block carrying instructions<summary>Manual Setup (if you prefer)</summary> > **Tip:** Run `nlm setup add json` for an interactive wizard that generates the right JSON snippet for your tooFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/mcp/tools/setup.py:64 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/notebooklm_tools/services/sources.py:294 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files~/.ssh, ~/.aws, ~/.gnupg, ~/.config, or ~/.notebooklm-mcp-cli.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/utils/cdp.py:540 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/cli/commands/setup.py:324 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionsrc/notebooklm_tools/cli/ai_docs.py:968 · File type combined with upload action — agent may exfiltrate local data files…saved with default names (e.g., `audio_<id>.mp3`, `video_<id>.mp4`, `report_<id>.txt`). Use `--output` to specify custom filenames. 17. **Streaming downloads** - All downloads use e…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/notebooklm_tools/cli/ai_docs.py:531 · File type combined with upload action — agent may exfiltrate local data files- Report: `.txt` or `.md` (Briefing Doc, Study Guide, Blog Post)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/notebooklm_tools/cli/commands/skill.py:240 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"""Install/update AGENTS.md format (append with markers)."""Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/cli/commands/setup.py:486 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/notebooklm_tools/services/downloads.py:91 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(e.g. ~/.ssh/known_hosts is inside HOME but still blocked).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/cli/commands/setup.py:208 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/cli/commands/setup.py:708 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Fake instruction boundary tagsrc/notebooklm_tools/data/SKILL.md:316 · Fake instruction boundary tag# Each --slide value must be: '<slide-number> <instruction>'Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/mcp/tools/server.py:16 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈7,100 tok
1 file · 80 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for notebooklm-enterprise-mcp@1.0.8 as of 27 h ago. This is the package itself, not its dependencies.

What would make this Verified

3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim robiton: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim robitonPropose a patch to the maintainer