document-forensics

Analyze document collections for provenance, anomalies, redactions, and cross-document inconsistencies.

4|1|Updated Jan 27, 2026

Search Tags:#validation #metadata #document analysis #anomaly detection #redaction #forensics

Ready to run

npx skills add https://github.com/AreteDriver/ai-skills --skill document-forensics

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: document-forensics
Source: https://github.com/AreteDriver/ai-skills/tree/main/agents/analysis/document-forensics
Command: npx skills add https://github.com/AreteDriver/ai-skills --skill document-forensics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdfplumber, cv2, dateutil, exiftool, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a structured methodology to deeply analyze document collections, uncovering hidden information, inconsistencies, and potential fabrications that might be missed by standard review.

Core Features & Use Cases

Provenance Analysis: Verify the origin and authenticity of documents by examining metadata.
Anomaly Detection: Identify unusual patterns in document creation times, content, or structure.
Redaction Detection: Find both visual and subtle "white-box" redactions.
Cross-Document Validation: Detect contradictions and corroborations between different documents.
Use Case: Analyze a set of leaked corporate documents to identify inconsistencies in executive travel claims, detect doctored financial reports, and build a timeline of events.

Quick Start

Use the document-forensics skill to perform provenance analysis on the attached document 'financial_report_2023.pdf'.

Frequently Asked Questions about document-forensics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I detect redactions and metadata anomalies in a PDF document?▼

Document forensics detects redactions and metadata anomalies by systematically extracting embedded metadata using pdfplumber and exiftool, then applying image analysis to identify visual or subtle white-box redactions across the file collection.

What is cross-document validation and how does it uncover inconsistencies?▼

Cross-document validation is an investigative workflow technique that compares text and metadata across a document collection to detect contradictions, corroborate provenance, and uncover hidden fabrications in legal or financial corpora.

Can I use exiftool and pdfplumber for provenance analysis on financial reports?▼

Yes, the document forensics workflow leverages exiftool and pdfplumber to perform provenance analysis on financial reports, verifying document origin and authenticity by examining embedded metadata and creation timestamps.

What is the best way to analyze a leaked corporate document collection for doctored files?▼

The best way to analyze a leaked document collection is using an 8-step investigative workflow that guides provenance analysis, anomaly detection, redaction identification, and cross-document validation to build a reliable timeline of events.

Do I need cv2 and dateutil installed to perform image analysis for document forensics?▼

Yes, you need cv2 and dateutil installed to support the document forensics workflow, as cv2 handles image analysis for visual redaction detection and dateutil processes chronological anomalies in document metadata.

What are the limitations of anomaly detection when analyzing document creation times?▼

Anomaly detection for document creation times relies heavily on intact metadata; if files have been stripped of exif data or had timestamps deliberately falsified, the validation process may require cross-referencing text content to confirm inconsistencies.