More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Jupyter Notebook Safety Check

    1

    This skill finds those leaks and seven other notebook problems before the file goes to GitHub, a ticket or Kaggle, and tells you how to fix each one.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Jupyter Notebook Safety Check

    Jupyter Notebook Safety Check

    Example session with this skill installed

    Check this project with jupyter-notebook-safety-check.

    • Read your context and instructions
    • Compiled the jupyter notebook safety

    $ python3 scripts/check_notebook.py examples/risky
    BLOCK notebooks/churn_analysis.ipynb:43 N01 SECRET_IN_CELL
    cell 3: DB_PASSWORD = "<redacted>"
    Why: A password, API key or token is written in a cell: an assignment (OPENAI_API_KEY = "..."), a keyword argument (api_key="..."), environ["NAME"] = "...", %env NAME=value, auth=(user, password), a URL with user:password@ (also in %sql), a Bearer token, or a known key format (ghp_, sk-, AKIA, xoxb-, hf_, a Kaggle key, a private key). Notebooks are shared, uploaded and committed more than other code, and anyone with the file can use the secret.
    Safer: Read secrets at run time from environment variables, getpass.getpass(), a .env file loaded with python-dotenv and listed in .gitignore, or Colab's Secrets panel (google.colab.userdata.get). Then revoke and replace the secret, because git history and .ipynb_checkpoints copies still hold it.

    BLOCK notebooks/churn_analysis.ipynb:96 N02 SECRET_IN_OUTPUT
    BLOCK notebooks/churn_analysis.ipynb:2840 N02 SECRET_IN_OUTPUT
    BLOCK notebooks/churn_analysis.ipynb:2849 N01 SECRET_IN_CELL
    BLOCK notebooks/churn_analysis.ipynb:2902 N03 SECRET_IN_METADATA
    BLOCK notebooks/churn_analysis.ipynb:2917 N03 SECRET_IN_METADATA
    BLOCK notebooks/support_summaries.ipynb:39 N02 SECRET_IN_OUTPUT
    BLOCK notebooks/support_summaries.ipynb:44 N01 SECRET_IN_CELL
    REVIEW notebooks/churn_analysis.ipynb:28 N12 UNPINNED_INSTALL
    REVIEW notebooks/churn_analysis.ipynb:29 N13 DOWNLOAD_PIPED_TO_SHELL
    REVIEW notebooks/churn_analysis.ipynb:61 N11 PERSONAL_DATA_IN_OUTPUT
    REVIEW notebooks/churn_analysis.ipynb:81 N15 PERSONAL_PATH
    REVIEW notebooks/churn_analysis.ipynb:117 N14 LARGE_OUTPUT
    REVIEW notebooks/churn_analysis.ipynb:2836 N17 SAVED_ERROR_OUTPUT
    REVIEW notebooks/churn_analysis.ipynb:2841 N15 PERSONAL_PATH
    REVIEW notebooks/churn_analysis.ipynb:2854 N16 CELLS_RUN_OUT_OF_ORDER
    REVIEW notebooks/churn_analysis.ipynb:2899 N15 PERSONAL_PATH
    REVIEW notebooks/support_summaries.ipynb:26 N12 UNPINNED_INSTALL

    (Each finding also has Why and Safer lines, as in the first one.)
    Verdict: BLOCK. Checked 2 files, 2 with Jupyter notebook content.
    This is a static check of file text. NOT FLAGGED is not a guarantee.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    You deleted the line with your API key, but the notebook still holds it: the output of the cell that printed it, the traceback that shows postgresql://analyst:password@db, the papermill parameters in the metadata, and the .ipynb_checkpoints copy. This skill finds those leaks and seven other notebook problems before the file goes to GitHub, a ticket or Kaggle, and tells you how to fix each one.

    Your agent runs a scanner on your .ipynb files (nbformat 4 and 3, from JupyterLab, Jupyter Notebook, VS Code, Colab, Kaggle and papermill, including .ipynb_checkpoints copies). It reads the notebook's JSON itself: code, markdown and raw cells, every output type (stream, execute_result, display_data, error), notebook and cell metadata, and saved widget state. Each finding names the cell and the exact line of the .ipynb file. It never runs the notebook or starts a kernel. It returns BLOCK, REVIEW, or NOT FLAGGED, with the file, line, reason, and a safer approach. Secrets are never printed, and email addresses and phone numbers are only counted.

    What it checks

    BLOCK

    • N01: passwords, API keys and tokens written in cells (assignments, api_key= arguments, %env, auth= tuples, connection strings in %sql, Bearer tokens, Kaggle keys, ghp_, sk-, AKIA, hf_ and other known key formats, private keys)
    • N02: secrets saved in outputs (printed keys, environment dumps, env: NAME=value, tracebacks that show a connection string)
    • N03: secrets in metadata (papermill parameters, saved ipywidgets Password values)

    REVIEW

    • N11: email addresses and phone numbers in saved outputs
    • N12: pip, %pip and conda installs without an exact version, and git URLs without a tag or commit
    • N13: downloads piped into a shell or Python (!curl ... | bash)
    • N14: very large outputs, embedded images over 1 MB, or more than 5 MB of saved outputs
    • N15: home-folder paths (/Users/name, /home/name, C:\Users\name) in code, outputs and metadata
    • N16: cells run out of order (execution counts that go down)
    • N17: saved error tracebacks

    What's included

    • The scanner (Python 3.9+, standard library only)
    • A rules guide with the reason and safer approach for each rule
    • A risky and a safe example project with two notebooks each, and the real report the scanner produces on the risky one

    Limits It reads the notebook file as saved: it cannot see what images show, and it does not read Jupytext pairs, .env files or the data files a notebook loads. Notebooks up to 20 MB are checked; in very large outputs only the first 1,000,000 characters are searched for secrets. NOT FLAGGED is not a guarantee.

    Static check of notebook JSON. Secrets built at run time or split across variables, text inside images, and phone numbers in unusual formats are not found. NOT FLAGGED is not a guarantee.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files

    Runs one local Python script in the terminal. It reads your project's files, writes nothing, and makes no network calls. The example notebooks include clearly fake, inert keys and passwords (not-a-real-...), fake names, emails on a .notreal domain and 555 phone numbers for the scanner to find. They are never run.

    Listed5 days ago
    Updated4 days ago

    What's inside

    Frequently Asked Questions

    No. The script reads local files only and makes no network calls.

    No. It only reports. Your agent changes files only if you ask it to.

    Any agent that supports SKILL.md skills and can run a terminal command, such as Claude Code. It needs Python 3.9 or newer and nothing else.

    No. It reads the .ipynb JSON as text, including saved outputs. It never starts a kernel or runs a cell.

    BLOCK: fix it before you ship. REVIEW: check it before release. NOT FLAGGED: no rule matched. It is a static check, so NOT FLAGGED is not a guarantee.

    The scanner, a rules guide with the reason and safer approach for every rule, a risky and a safe example notebook, and the real report the scanner prints on the risky example.

    New in Security