- Home
- Skills
- Data & Databases
- CSV and Spreadsheet Data Privacy Check
More screenshots
Works with the AI Agents you already use
CSV and Spreadsheet Data Privacy Check
This skill finds those before the file leaves your hands, and tells you in plain words what to remove or fix.
$5
CSV and Spreadsheet Data Privacy Check
Example session with this skill installed
Check this project with csv-data-privacy-check.
- Read your context and instructions
- Compiled the csv and spreadsheet
- Generated the data export
$ python3 scripts/check_csv.py examples/risky
BLOCK exports/customers.csv:2 D02 CARD_NUMBER
Column F 'card_number': card numbers that pass the Luhn check in 2 cells (F2, F3).
Why: A cell holds a payment card number: 13 to 19 digits that pass the Luhn check and start the way a real card brand does (Visa, Mastercard, American Express, Discover, JCB, Diners, UnionPay, Maestro, Mir, RuPay, Verve). PCI DSS requires stored card numbers to be unreadable (masked, truncated, tokenized or encrypted), and anyone who gets the file can try to use the cards.
Safer: Remove the column, or keep only the last four digits or the payment provider's token. If the file was already shared, tell whoever is responsible for card data so they can follow their incident process.
BLOCK exports/customers.csv:2 D04 SECRET_IN_DATA
BLOCK exports/customers.csv:3 D01 FORMULA_IN_CELL
BLOCK exports/events.jsonl:1 D04 SECRET_IN_DATA
BLOCK exports/payouts.tsv:2 D03 IBAN
REVIEW exports/customers.csv:1 D17 HEADER_PROBLEMS
REVIEW exports/customers.csv:2 D11 EMAIL_ADDRESSES
REVIEW exports/customers.csv:2 D12 PHONE_NUMBERS
REVIEW exports/customers.csv:4 D13 NATIONAL_ID_NUMBERS
REVIEW exports/customers.csv:4 D16 MIXED_DATE_FORMATS
REVIEW exports/customers.csv:5 D15 BROKEN_ROWS
REVIEW exports/customers.csv:6 D14 DUPLICATE_ROWS_OR_IDS
REVIEW exports/customers.csv:7 D14 DUPLICATE_ROWS_OR_IDS
REVIEW exports/events.jsonl:1 D11 EMAIL_ADDRESSES
REVIEW exports/events.jsonl:3 D15 BROKEN_ROWS
(Each finding also has Why and Safer lines, as in the first one.)
Verdict: BLOCK. Checked 3 files, 3 with tabular data content.
This is a static check of file text. NOT FLAGGED is not a guarantee.
customers.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
A customer export goes to a vendor, and nobody noticed the card_number column, the password hashes, or a "name" that a visitor typed as =HYPERLINK(...), which can run as a formula when someone opens the CSV in Excel. This skill finds those before the file leaves your hands, and tells you in plain words what to remove or fix.
Your agent runs a scanner on a file or a whole folder of .csv, .tsv, .jsonl and .xlsx files. It works out the separator by itself (comma, semicolon, tab or |), reads files saved by Excel (with a BOM, UTF-16, or quoted values that hold commas and line breaks), and reads every worksheet of an .xlsx workbook, hidden ones included. Each finding names the file, the column and the cells as you see them in Excel (C7) or the JSONL line, with a count, the reason and a safer approach. It never prints what is in a cell, never changes the file and never uses the network. It returns BLOCK, REVIEW, or NOT FLAGGED.
What it checks
BLOCK
- D01: cells that start with = + - @ and call a function or another program (CSV formula injection, DDE)
- D02: payment card numbers that pass the Luhn check and fit a real card range, length and grouping
- D03: IBANs with the right length for their country and valid check digits
- D04: columns of passwords, password hashes, API keys or tokens, and keys in known formats
REVIEW
- D11: email addresses, counted per column
- D12: phone numbers (phone-named columns and +country numbers)
- D13: national ID numbers (US SSN, UK National Insurance, passport and ID columns)
- D14: rows that repeat exactly, and repeated values in an ID column
- D15: rows with the wrong number of columns, unclosed quotes, lines that are not valid JSON
- D16: one column with dates in several formats (2024-03-01 next to 03/01/2024, day-first next to month-first)
- D17: header problems: missing or repeated names, extra spaces, no header row
- D18: files larger than the scanner reads (more than 100,000 rows)
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 set of sample exports (CSV, TSV and JSONL), and the real report the scanner produces on the risky set
Limits It reads the first 100,000 rows of each file or worksheet (at most 2,000,000 cells) and says so when a file has more. .xlsx files over 50 MB, old .xls, password-protected workbooks, .ods and JSON array files are not read. Names, street addresses and dates of birth written as free text are not detected. NOT FLAGGED is not a guarantee.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
Static check of file contents. Reads the first 100,000 rows per file or sheet; free-text personal data such as names and addresses, and card numbers Excel already rounded, are not detected. NOT FLAGGED is not a guarantee.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
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
Permissions
Runs one local Python script in the terminal. It reads your project's files, writes nothing, and makes no network calls. The example files contain only made-up names, reserved example.com email addresses, phone numbers from the UK fiction range, card numbers and IBANs built for the test (bank code NOTR), and clearly fake passwords (not-a-real-...). The sample formula points at attacker.example and does nothing. Nothing is uploaded or changed.