SKILLEMALL.ai
GitHub ↗ RU Sign in

DC notebooklm-cli

Search and answer questions over documents already uploaded to NotebookLM using the nlm CLI. Use when users ask to find information, summarize sources, or query a specific NotebookLM notebook.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: lhquangit v0.1.4 5 files · 2 scripts body ≈ 881 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, consistency, progress reporting

IntegrationInfrastructureWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
D
57/100
safety, quality, tests
Safety 60%
42
Quality 40%
80
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 9

  • high Exfiltration intent-browser-credential-store docs/GUIDELINE.md:90
    Accesses a browser credential / cookie store
    NotebookLM requires Google cookies. You must prepare auth on a machine with Chrome:
Medium and low: 8
  • medium Dangerous commands cmd-privilege docs/GUIDELINE.md:125
    Privilege escalation / world-writable permissions
    sudo cp ./notebooklm-auth.json /etc/openclaw/notebooklm-auth.json
  • medium Dangerous commands cmd-privilege docs/GUIDELINE.md:126
    Privilege escalation / world-writable permissions
    sudo chown root:openclaw /etc/openclaw/notebooklm-auth.json
  • medium Dangerous commands cmd-privilege docs/GUIDELINE.md:127
    Privilege escalation / world-writable permissions
    sudo chmod 640 /etc/openclaw/notebooklm-auth.json
  • medium Dangerous commands cmd-privilege scripts/bootstrap_vps_systemd_one_liner.sh:207
    Privilege escalation / world-writable permissions
    sudo mv /tmp/notebooklm-auth-inject.sh "${INJECT_BIN}"
  • medium Dangerous commands cmd-privilege scripts/bootstrap_vps_systemd_one_liner.sh:208
    Privilege escalation / world-writable permissions
    sudo chown "${TARGET_USER}":"${TARGET_USER}" "${INJECT_BIN}"
  • medium Dangerous commands cmd-privilege scripts/bootstrap_vps_systemd_one_liner.sh:209
    Privilege escalation / world-writable permissions
    sudo chmod 0755 "${INJECT_BIN}"
  • medium Dangerous commands cmd-privilege scripts/bootstrap_vps_systemd_one_liner.sh:253
    Privilege escalation / world-writable permissions
    sudo chown "${TARGET_USER}":"${TARGET_USER}" "${OPENCLOW_CFG}" || true
  • medium Dangerous commands cmd-privilege scripts/bootstrap_vps_systemd_one_liner.sh:259
    Privilege escalation / world-writable permissions
    sudo chown root:root "${AUTH_FILE}"

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 63/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (notebooklm-cli) differs from the folder (notebooklm-cli-cookies)
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Failures and branches. 9 branches
  • 100Steps. 34 steps
  • 100Execution cost. Instruction body is 881 tokens
  • 100Running it twice. Mutating operations check current state

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 192: enough signal without eating the budget
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 34 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

External checks

ClawHub: suspicious
The skill is mostly aligned with querying NotebookLM, but it needs Review because it forwards raw Telegram commands to a CLI and ships privileged VPS setup scripts that handle reusable Google session cookies.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026