Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Liberty91LTD/cti-skills --skill carding-financial-fraudgit clone --depth 1 https://github.com/Liberty91LTD/cti-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/liberty91ltd/cti-skills/carding-financial-fraud)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/carding-financial-fraud"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/carding-financial-fraud/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/carding-financial-fraud"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/carding-financial-fraud.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.02594 |
| Opus 5 | $0.00034 | $0.01297 |
| Sonnet 5 | $0.00013 | $0.00519 |
| Haiku 4.5 | $0.00007 | $0.00259 |
Grade A, and why
carding-financial-fraud scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carding & Financial Fraud
Executive Summary
Carding and financial fraud represent one of the oldest and most mature cybercriminal ecosystems, encompassing the theft, trade, and monetization of payment card data and financial credentials. The ecosystem spans from initial data theft (via digital skimming, POS malware, phishing, and database breaches) through underground marketplace trading to ultimate monetization via card-not-present (CNP) fraud, money mule networks, and reshipping schemes. The shift toward EMV chip cards largely eliminated traditional card cloning for in-person fraud in developed markets, pushing the ecosystem heavily toward CNP fraud in e-commerce, which now represents the vast majority of card fraud losses globally — estimated at over $30 billion annually.
The digital skimming landscape, dominated by the umbrella term "Magecart," continues to evolve with threat actors injecting malicious JavaScript into e-commerce payment pages through compromised third-party scripts, CMS vulnerabilities, and supply chain attacks. Card shops and carding forums provide the marketplace infrastructure, with BidenCash emerging as a prominent card shop known for large-scale free dumps to attract customers. The Genesis Market takedown in Operation Cookie Monster (April 2023) disrupted a major marketplace for stolen credentials and browser fingerprints, though alternatives rapidly filled the gap.
The fraud ecosystem increasingly overlaps with other cybercriminal domains. Infostealer malware feeds card data and banking credentials directly into fraud pipelines. Business Email Compromise (BEC) operators share techniques and money mule networks with carding groups. SIM swapping enables account takeover for financial fraud and cryptocurrency theft. The emergence of Fraud-as-a-Service (FaaS) platforms has lowered barriers to entry, offering turnkey fraud toolkits, tutorials, and operational support to less sophisticated actors.
Key Actors
| Actor/Entity | Type | Notable Characteristics | Status |
|---|---|---|---|
| BidenCash | Card Shop | Major marketplace; known for marketing via large free card dumps (millions of records); Tor-based | Active |
| Joker's Stash | Card Shop | Formerly dominant card shop; voluntarily retired February 2021 | Defunct |
| BriansClub | Card Shop | Major card shop; was itself breached in 2019 exposing 26M card records | Status unclear |
| Genesis Market | Credential/Bot Market | Sold browser fingerprints and credentials; seized in Operation Cookie Monster April 2023 | Seized |
| Russian Market | Log/Credential Shop | Major marketplace for infostealer logs, RDP access, and card data | Active |
| Magecart Groups | Digital Skimming Collective | Umbrella term for multiple groups conducting web-based card skimming | Active (various) |
| FIN7 | Cybercrime Group | Sophisticated group with ties to POS malware (Carbanak/FIN7 campaigns); members arrested but operations continued | Partially disrupted |
| Scattered Spider | Cybercrime Collective | SIM swapping, social engineering, financial fraud; young Western actors | Active |
| Various BEC Networks | Fraud Operations | West African (Yahoo Boys) and Eastern European networks conducting BEC and romance fraud | Active |
| SIM Swapping Crews | Account Takeover | Loosely organized groups bribing telecom employees or exploiting SS7 | Active |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 123 lines · 67 tokens per session scan A 566e2b48a119
carding-financial-fraud is a skill published in the GitHub repository Liberty91LTD/cti-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 2,594 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-pricing-strategy
A pricing-strategy diagnosis assistant that examines supplied material and produces a summary, findings, recommended actions, and reusable deliverables.
ai-financial-marketing-compliance-review
A financial marketing compliance review assistant for examining pricing or marketing material for financial concerns.
ai-financial-report-anomaly-question-list
A financial pricing diagnosis assistant for examining whether a price is likely to avoid losses.
ai-insurance-policy-faq-explainer
A risk-review helper for explaining questions about insurance policies and their possible risks. It produces summaries, diagnoses, recommended actions, and reusable deliverables from supplied material.
ai-investment-research-material-compare
A material-comparison helper for reviewing investment research documents or other supplied materials. It produces summaries, diagnoses, recommended actions, and reusable deliverables.
ai-public-company-due-diligence-summary
A due-diligence summary assistant for public companies. Due diligence is the process of checking a company and its information before making a business or investment decision.