Csv pii scanner
Production-Ready Agent Skills : product analytics, growth experiments, CRM, research synthesis, postmortems, data contracts, SaaS spend, compliance, architecture maps, and LLM eval and many more.
npx -y skills add sisodiabhumca/agent-skills --skill csv-pii-scannerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Vendor-neutral skill to scan CSV exports for likely PII columns and risky values, producing a remediation-focused report.
SKILL.md
1.1 KB, as published. Nobody here has run it
When to invoke
- When reviewing CSV exports before sharing externally.
- When building a data-loss-prevention (DLP) checklist for analytics datasets.
Inputs needed
--input: Path to a CSV file.- Optional
--out: Path to write a JSON report. - Optional
--max-rows: Max rows to sample (default 2000).
Workflow
- Read CSV headers and sample up to N rows.
- For each column, score risk using:
- Header keywords (email, phone, ssn, address, dob, name).
- Value patterns (email-like, phone-like, IP address, credit card-like, SSN-like).
- Output suspected PII columns with examples (redacted) and suggested remediation.
Output format
JSON with:
suspected_columns: list of{column, risk, reasons, examples_redacted}.summary: counts by risk.
Guardrails
- Redact example values in output.
- Use heuristics only; results are probabilistic.
Reference code
csv_pii_scanner.py