auditai-sdk

v0.2.6 suspicious
5.0
Medium Risk

EU AI Act Compliance + AI Monitoring SDK — wrap Claude/GPT, track cost & latency, generate Art. 26 reports

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package exhibits moderate risks due to network and shell execution vulnerabilities, which could potentially be exploited. However, there's no evidence of obfuscation or credential misuse.

  • Moderate network risk due to urllib usage
  • Significant shell risk from subprocess calls
Per-check LLM notes
  • Network: The use of urllib to make network requests is common but could be a vector for data exfiltration if not properly secured.
  • Shell: Executing external commands via subprocess can pose significant risks if not controlled properly, potentially allowing for arbitrary code execution.
  • Obfuscation: No obfuscation patterns detected, indicating low risk of malicious activity.
  • Credentials: No credential harvesting patterns detected, suggesting safe handling of sensitive information.
  • Metadata: The package shows signs of potential inactivity or newness with an author having minimal information and a low presence in the repository.

📦 Package Quality Overall: Low (4.8/10)

◈ Medium Test Suite 6.0

Partial test coverage signals detected

  • 1 test file(s) detected (e.g. test_core.py)
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (2719 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

  • 28 type-annotated function signatures detected in source
◈ Medium Multiple Contributors 6.0

Limited contributor diversity

  • 2 unique contributor(s) across 16 commits in marcduboistech-eng/auditai
  • Two distinct contributors found

🔬 Heuristic Checks

⚠ Outbound Network Calls score 6.0

Found 4 network call pattern(s)

  • " upstream_req = urllib.request.Request( upstream_url, data=raw_body, header
  • try: with urllib.request.urlopen(upstream_req, timeout=120) as resp:
  • try: req = urllib.request.Request(upstream_url, headers=upstream_headers)
  • headers) with urllib.request.urlopen(req, timeout=30) as resp: raw =
✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 2.0

Found 1 shell execution pattern(s)

  • e__), "dashboard.py") subprocess.run([ sys.executable, "-m", "streamlit", "run", _das
✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

No author email provided

✓ Suspicious Page Links

All external links appear legitimate

⚠ Git Repository History score 2.5

Git history flags: Repository has zero stars and zero forks

  • Repository has zero stars and zero forks
⚠ 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 auditai-sdk 
Create a mini-application called 'AI Monitor Pro' that leverages the 'auditai-sdk' package to ensure compliance with the EU AI Act while providing developers with real-time monitoring capabilities for their AI services. This application will integrate with popular AI models like Claude and GPT to offer a suite of features designed to streamline compliance processes and enhance operational efficiency.

Step-by-Step Application Requirements:
1. Integration Setup: Begin by setting up the integration between 'AI Monitor Pro' and the 'auditai-sdk'. Ensure that the application can authenticate and connect to AI models like Claude and GPT using the SDK.
2. Real-Time Cost Tracking: Implement a feature that monitors and tracks the costs associated with running AI models in real-time. This should include breaking down costs per request and displaying them in a user-friendly dashboard.
3. Latency Measurement: Add functionality to measure the latency of each AI model request. Display these measurements alongside the cost tracking information to give users insight into performance metrics.
4. Compliance Reporting: Utilize the 'auditai-sdk' to automatically generate Article 26 compliance reports. These reports should detail the usage of AI models over a specified period and include relevant data points as required by the EU AI Act.
5. User Interface: Design a clean, intuitive UI that allows users to easily access all features. Include options to view cost and latency data, manage API keys, and download compliance reports.

Suggested Features:
- Customizable alert system for high-cost or high-latency requests.
- Historical data analysis tools to identify trends and optimize AI usage.
- Support for multiple AI models through the 'auditai-sdk'.
- Export functionality for compliance reports in various formats (PDF, CSV).

How to Use 'auditai-sdk':
- For authentication and connection setup, utilize the SDK's built-in methods to securely handle API keys and other sensitive information.
- To track costs and latency, leverage the SDK's monitoring APIs which provide detailed insights into each request made to AI models.
- For generating compliance reports, use the SDK's reporting tools which automatically compile necessary data according to EU AI Act guidelines.

💬 Discussion Feed

Leave a comment

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