ebay-fraud-analysis

ebay-fraud-analysis is a command for Claude Code from jbwashington/ebay-mcp. It costs 10 tokens per session (1,310 once invoked), scanned A, original, MIT.

A command that reviews an eBay buyer's account for signs of fraud or repeated failure to pay for purchases.

In plain words
What is it for?
Use it with a buyer username or order ID to assess transaction risk and identify patterns such as a new account, poor feedback, or unpaid purchases.
Why use it?
It gathers account details, feedback, transactions, account age, and shipping information in one review, so you can spot warning signs before completing a sale.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Part of the ebay-listing-automation plugin — 13 commands, 3 hooks shipped together

Good fit Use it with a buyer username or order ID to assess transaction risk and identify patterns such as a new account, poor feedback, or unpaid purchases.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jbwashington/ebay-mcp/ebay-fraud-analysis
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jbwashington/ebay-mcp

Made for: Claude Code.

Or install ebay-listing-automation, the plugin that ships this one along with the rest of its 13 commands, 3 hooks.

Wrote 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.

agentmods badge for ebay-fraud-analysis

README.md
[![agentmods](https://agentmods.dev/badge/commands/jbwashington/ebay-mcp/ebay-fraud-analysis/github.svg)](https://agentmods.dev/commands/jbwashington/ebay-mcp/ebay-fraud-analysis)
Your own site
<a href="https://agentmods.dev/commands/jbwashington/ebay-mcp/ebay-fraud-analysis"><img src="https://agentmods.dev/badge/commands/jbwashington/ebay-mcp/ebay-fraud-analysis/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.

agentmods 80×15 button for ebay-fraud-analysis

Your own site · 80×15
<a href="https://agentmods.dev/commands/jbwashington/ebay-mcp/ebay-fraud-analysis"><img src="https://agentmods.dev/badge/commands/jbwashington/ebay-mcp/ebay-fraud-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,310 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.01310
Opus 5 $0.00005 $0.00655
Sonnet 5 $0.00002 $0.00262
Haiku 4.5 $0.00001 $0.00131

Measured 10d ago against content hash c6278a2d1fb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ebay-fraud-analysis 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 10d 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.

commands/ebay-fraud-analysis.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

eBay Fraud Analysis

Analyze a buyer's account to assess fraud risk, identify deadbeat bidder patterns, and help you make informed decisions about transactions.

Task

  1. Get buyer information from argument $1:

    • If it's a username: analyze that user directly
    • If it's an order ID: extract buyer from order first
    • If not provided: ask user for username or order ID
  2. Use eBay MCP tools to gather buyer data:

    • Get buyer account information
    • Fetch feedback history (positive, neutral, negative)
    • Get recent transaction history
    • Check account age
    • Verify shipping address if available
  3. Calculate Risk Score (0-100) based on:

    Account Age (30% weight):

    • < 7 days: 30 points
    • 7-30 days: 20 points
    • 30-90 days: 10 points
    • 90+ days: 0 points

    Feedback Score (25% weight):

    • 0 feedback: 25 points
    • 1-5 feedback: 15 points
    • 6-25 feedback: 5 points
    • 26+ feedback: 0 points

    Feedback Percentage (20% weight):

    • < 95%: 20 points
    • 95-97%: 10 points
    • 98-99%: 5 points
    • 100% (but < 10 transactions): 10 points
    • 100% (10+ transactions): 0 points

    Recent Negative Feedback (15% weight):

    • Negative in last 30 days: 15 points
    • Negative in last 90 days: 10 points
    • Negative in last year: 5 points
    • No negatives: 0 points

    Geographic Risk (10% weight):

    • International high-risk country: 10 points
    • International standard risk: 5 points
    • Domestic: 0 points
  4. Identify Red Flags:

    • ⚠️ Zero or minimal feedback (< 5)
    • ⚠️ Account age < 30 days
    • ⚠️ Negative feedback as buyer
    • ⚠️ Unpaid item cases in history
    • ⚠️ International shipping to high-risk countries
    • ⚠️ Multiple recent negative feedbacks
    • ⚠️ Suspicious bidding patterns
    • ⚠️ Private feedback settings
  5. Generate Risk Assessment:

    • Risk Score: X/100
    • Risk Level: Low (0-25) | Medium (26-50) | High (51-75) | Critical (76-100)
    • Red Flags: List all identified issues
    • Account Summary: Age, feedback, history
    • Recommendation: Accept | Caution | Require Payment | Cancel

Read the full file on GitHub · 174 lines

Changes

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.

  1. 10d ago First seen · 174 lines · 10 tokens per session scan A c6278a2d1fb3

Subscribe to this mod's changes

ebay-fraud-analysis is a command published in the GitHub repository jbwashington/ebay-mcp (14 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 1,310 once invoked, about $0.0001 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.