Menu

Individual skill

leak-record-classifier

0upvotes

Classify a client-provided leaked/breach-database CSV export (Maltego D4 format) against a subject's identity anchors (SSN, DOB, address, email) into confidence tiers, producing cleaned/filtered-out CSVs and a color-coded Excel deliverable. Use when: analyzing a leaked-records CSV, a Maltego D4 export, breach data for a named subject, "leaked database export", "reformat this CSV of records", filtering false-positive name matches out of a data broker/breach dump. NOT for: live OSINT collection (see the osint skill), report narrative writing (case-specific, stays bespoke per subject), or non-CSV evidence (see extract-intake.py for PDF/DOCX/image verbatim extraction).

skills/leak-record-classifier/SKILL.md

Read pinned source

Source commit f38c4df19c0c0b3b9fcc1f8529801db153f795fa

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 5, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
74
Repository last updated
Nov 2, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Leak Record Classifier

Shared scaffold for the recurring "client hands us a leaked-database CSV, find
the records that belong to our subject" task. Consolidated 2026-07-21 after two
cases (`case-001-example`, `case-001-example`) independently
rewrote the same ~250-line Maltego-parsing + classification + Excel-writing
scaffold from scratch, differing only in each subject's identity anchors.

## Prerequisite -- ingest first (enforced by a hook, not optional)

The source CSV must already be registered as an EV-NNNN item and deterministically
extracted before you write or run a classification script against it:

```bash
Back to top