aml-ai-mcp

v1.0.5 suspicious
4.0
Medium Risk

6AMLD + UK MLR 2017 + FinCEN BSA AML/CFT compliance for AI-enabled transaction monitoring, sanctions screening, PEP screening.

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package has minimal direct risks but exhibits signs of potential supply-chain compromise due to low repository activity and a single contributor. Further investigation into the legitimacy of the service and the credentials required for subscription is recommended.

  • Low repository activity and single contributor
  • Subscription-based model requiring payment
Per-check LLM notes
  • Network: No network calls detected, which is normal if the package does not require internet access.
  • Shell: No shell execution patterns detected, indicating the package does not execute external commands.
  • Obfuscation: No obfuscation patterns detected, indicating low risk of malicious activity.
  • Credentials: No credential harvesting patterns detected, indicating low risk of malicious activity.
  • Metadata: The repository's low activity and single contributor suggest potential risk, especially with the author's new or inactive status.

📦 Package Quality Overall: Low (3.0/10)

○ Low Test Suite 1.0

No test suite detected

  • No test files or test-runner configuration detected
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (2793 chars)
○ Low Contributing Guide 2.0

No contributing guide or governance files found

  • No CONTRIBUTING, CODE_OF_CONDUCT, or governance files found
◈ Medium Type Annotations 5.0

Partial type annotation coverage

  • 8 type-annotated function signatures (partial)
○ Low Multiple Contributors 2.0

Single-author or unverifiable project

  • 1 unique contributor(s) across 3 commits in CSOAI-ORG/aml-ai-mcp
  • Single author with few commits — possibly a personal or throwaway project

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

✓ Code Obfuscation

No obfuscation patterns detected

✓ Shell / Subprocess Execution

No shell execution patterns detected

✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: meok.ai>

✓ Suspicious Page Links

All external links appear legitimate

⚠ Git Repository History score 5.0

Git history flags: Repository has zero stars and zero forks

  • Repository has zero stars and zero forks
  • Single contributor with only 3 commit(s) — possibly throwaway account
⚠ Maintainer History score 4.0

2 maintainer concern(s) found

  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with aml-ai-mcp 
Create a mini-application named 'AMLComplianceChecker' that leverages the 'aml-ai-mcp' Python package to perform real-time AML/CFT compliance checks on financial transactions. This tool will be designed to assist financial institutions in identifying suspicious activities such as money laundering, terrorist financing, and other financial crimes.

The application should include the following features:
1. User Interface: Develop a simple web-based interface using Flask or Django where users can input details of financial transactions (e.g., transaction amount, parties involved).
2. Compliance Checks: Utilize the 'aml-ai-mcp' package to run compliance checks based on 6AMLD, UK MLR 2017, and FinCEN BSA standards. These checks should include AI-enabled transaction monitoring, sanctions screening, and PEP (Politically Exposed Persons) screening.
3. Risk Assessment: Based on the results of the compliance checks, the application should provide a risk assessment score indicating the likelihood of the transaction being associated with illegal activity.
4. Reporting: Implement a feature that generates a report summarizing the compliance check results, including any flagged issues and the risk assessment score.
5. Alerts: If a transaction fails one or more compliance checks, the application should send an alert via email or SMS to designated compliance officers.

Steps to Build the Application:
1. Set up a virtual environment and install necessary packages including Flask/Django, aml-ai-mcp, and any other required dependencies.
2. Design and develop the user interface allowing users to submit transaction data.
3. Integrate the 'aml-ai-mcp' package into your application to process transaction data and run compliance checks.
4. Implement logic to calculate a risk assessment score based on the compliance check outcomes.
5. Create a reporting module that generates comprehensive reports based on the compliance check results.
6. Add functionality for sending alerts to compliance officers if a transaction is flagged as high-risk.
7. Test the application thoroughly to ensure all features work correctly and securely handle user data.

💬 Discussion Feed

Leave a comment

No discussion yet. Be the first to share your thoughts!