gds-fraud-investigator

Name: gds-fraud-investigator
Availability: InStock
Author: hypertopos

Detect financial fraud and AML anomalies using GDS geometric analysis.

Updated Apr 9, 2026

Search Tags:#mcp #fraud #anomaly-detection #aml #typologies #geometric-analysis #cross-pattern

Ready to run

npx skills add https://github.com/hypertopos/hypertopos-skills --skill gds-fraud-investigator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gds-fraud-investigator
Source: https://github.com/hypertopos/hypertopos-skills/tree/main/gds-fraud-investigator
Command: npx skills add https://github.com/hypertopos/hypertopos-skills --skill gds-fraud-investigator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Investigate financial fraud and AML anomalies by applying geometric navigation over transaction spheres to surface anomalous actors, connections, and networks.

Core Features & Use Cases

Passive scanning across geometry layers to surface multi-source anomalies
Cross-pattern profiling and 360-degree entity view to map counterparties and networks
Typology-driven detection using motif scoring (structuring, cycle_2, cycle_3, fan_out, etc.) to triage investigations
Use Case: Screen a financial sphere for suspicious accounts, trace connections, and escalate high-risk suspects for deeper review

Quick Start

Load a financial sphere, run passive_scan to flag suspects, then inspect top results with cross_pattern_profile and score_motif for rapid triage.

Frequently Asked Questions about gds-fraud-investigator

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

FAQPage Schema

How does geometric analysis detect AML fraud and transaction anomalies?▼

Geometric analysis detects AML fraud by applying motif scoring and cross-pattern profiling over transaction spheres to surface multi-hop anomalous actor networks. It maps counterparties and triages investigations using typology-driven detection of structures like fan_out and cycle_3.

What is the best way to screen financial transactions for suspicious accounts?▼

The best way to screen financial transactions for suspicious accounts is running a passive scan across geometry layers. This flags high-risk suspects by mapping multi-source anomalies and 360-degree entity views before deeper cross-pattern profiling.

How do I trace multi-hop connections between suspicious accounts during an investigation?▼

Trace multi-hop connections by running cross_pattern_profile on flagged suspects. This maps counterparties and networks across the live sphere, confirming suspicious connections via motif ranking and cross-pattern tools.

Do I need an active MCP session to investigate AML typologies?▼

Yes, you need an active hypertopos MCP session with a loaded financial transaction sphere. The investigation requires access to edge tables, motif ranking, and cross-pattern tools to execute the three-phase screening workflow.

What AML typologies and motifs can I detect during a fraud investigation?▼

You can detect AML typologies including structuring, cycle_2, cycle_3, and fan_out motifs. Score_motif applies typology-driven detection to triage investigations by ranking these geometric patterns within the transaction sphere.

Can I use this anomaly detection approach without loading edge tables?▼

No, anomaly detection requires edge tables to access motif ranking and cross-pattern tools. Without a financial transaction sphere loaded in the MCP session, the geometric navigation cannot trace suspicious accounts or confirm networks.