Skills/PyPI/notebooklm-mcp-cli

notebooklm-mcp-cli@0.16.5

VERIFIED· install only

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

Registry PyPI (MCP server)Publisher jacob-bd · publishing for 290 daysInstalls 61,002Last detonated 37 min ago
$claude mcp add notebooklm-mcp-cli -- uvx notebooklm-mcp-cli
WatchReport an issue

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: Verified 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
NLM_AUTH_STORAGEConfiguration, not credentials: ALLOW_REAL_KEYSTORE, NLM_BROWSER, NLM_BROWSER_PATH, NLM_NO_COLOR, NLM_OUTPUT_FORMAT, NLM_PROFILE, NOTEBOOKLM_ALLOWED_FILE_DIRS, NOTEBOOKLM_ASYNC_QUERY_MAX_INFLIGHT, NOTEBOOKLM_BASE_URL, NOTEBOOKLM_BL, NOTEBOOKLM_COOKIES, NOTEBOOKLM_DISABLE_HEADLESS_REFRESH, NOTEBOOKLM_HL, NOTEBOOKLM_KEYSTORE_SERVICE_NAME, NOTEBOOKLM_LOCATION, NOTEBOOKLM_MCP_CLI_PATH, NOTEBOOKLM_MCP_HOST, NOTEBOOKLM_MCP_PATH, NOTEBOOKLM_MCP_PORT, NOTEBOOKLM_MCP_TRANSPORT, NOTEBOOKLM_PROJECT_ID, NOTEBOOKLM_QUERY_TIMEOUT, NOTEBOOKLM_RPC_OVERRIDES, PYTEST_CURRENT_TEST
Where it talks to
no vendor host named in the codeAlso google.com, youtube.com, example1.com, example2.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 as well as its own vendor. The guard injects NLM_AUTH_STORAGE only into requests to the host you bind (and its subdomains) and refuses the rest.

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

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 2026-11-14 and scored it 88/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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 detectedscripts/smoke_credential_store.py:296 · Python subprocess execution detectedp2 = subprocess.Popen(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/skill_package.py:115 · Python subprocess execution detectedreturn subprocess.run([opener, "-R", str(path)], check=False, timeout=5).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/notebooklm_tools/utils/cdp.py:1467 · Process kill command — agent can terminate processes"""Best effort to kill a process by PID."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/utils/cdp.py:697 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
URL to a private-network addresssrc/notebooklm_tools/utils/wsl.py:359 · URL to a private-network address — a LAN or development targetcdp_url: Full CDP HTTP URL (e.g., "http://172.20.112.1:9222")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/utils/cdp.py:786 · 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/utils/wsl.py:168 · Python subprocess execution detectedresult = subprocess.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:539 · 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 detectedscripts/smoke_credential_store.py:281 · Python subprocess execution detectedp1 = subprocess.Popen(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/firefox.py:102 · Python subprocess execution detectedreturn 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/utils/wsl.py:132 · 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/utils/cdp.py:760 · 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/utils/wsl.py:83 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
URL to a private-network addresssrc/notebooklm_tools/utils/wsl.py:436 · URL to a private-network address — a LAN or development targetFull CDP URL (e.g., "http://172.20.112.1:9222") or None.Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/utils/cdp.py:996 · Python subprocess execution detectedprocess = subprocess.Popen(args, **kwargs)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/utils/wsl.py:114 · 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/utils/wsl.py:205 · 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
Process kill commandsrc/notebooklm_tools/utils/cdp.py:1489 · Process kill command — agent can terminate processes# Process alive but CDP dead — zombie, kill itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/notebooklm_tools/utils/cdp.py:684 · 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:588 · 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
MEDIUM
Python subprocess execution detectedscripts/smoke_credential_store.py:463 · Python subprocess execution detectedproc = subprocess.run(Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈15,896 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

Not checked against OSV yet; the weekly check has not reached this version.