ai-dev-browser

v0.10.0 safe
4.0
Medium Risk

A browser for AI to develop web automation — human-like automation that works seamlessly in a world designed for humans

🤖 AI Analysis

Final verdict: SAFE

The package shows low risk indicators across most categories, with only obfuscation posing a moderate concern due to the use of unsafe-eval. There's no strong evidence of malicious intent.

  • No network or shell risks detected.
  • Moderate obfuscation risk due to unsafe-eval usage.
Per-check LLM notes
  • Network: No network calls detected, which is normal unless the package is expected to perform external communications.
  • Shell: No shell execution detected, indicating no immediate risk of command injection or similar attacks.
  • Obfuscation: The presence of 'unsafe-eval' suggests potential for code execution risks but may also be used legitimately for dynamic code evaluation.
  • Credentials: No clear patterns indicate credential harvesting, but always review how secrets are handled within the package.
  • Metadata: The maintainer has only one package, which may indicate a new or less active account, raising some suspicion but not conclusive evidence of malice.

📦 Package Quality Overall: Medium (6.6/10)

◈ Medium Test Suite 6.0

Partial test coverage signals detected

  • Test runner config found: pyproject.toml
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (9499 chars)
✦ High Contributing Guide 9.0

Has contribution guidelines and governance files

  • Governance file: security.py
  • Development Status classifier >= Beta
◈ Medium Type Annotations 5.0

Partial type annotation coverage

  • 1194 type-annotated function signatures detected in source
✦ High Multiple Contributors 8.0

Active multi-contributor project

  • 3 unique contributor(s) across 100 commits in sudoprivacy/ai-dev-browser
  • Small but multi-author team (3–4 contributors)

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

⚠ Code Obfuscation score 2.0

Found 1 obfuscation pattern(s)

  • 'unsafe-eval' which includes eval(), Function(), setTimeout() and setInterval() when called wi
✓ Shell / Subprocess Execution

No shell execution patterns detected

✓ 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

Repository sudoprivacy/ai-dev-browser appears legitimate

⚠ Maintainer History score 2.0

1 maintainer concern(s) found

  • Author "sudoprivacy" 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 ai-dev-browser 
Develop a mini-application called 'AI Web Explorer' that leverages the 'ai-dev-browser' package to automate web browsing tasks in a manner that mimics human behavior. This application should be able to navigate through websites, interact with elements on web pages, and perform complex actions like filling out forms, clicking buttons, and scrolling through content. Here are the steps and features to include:

1. **Setup Environment**: Install Python and the 'ai-dev-browser' package. Ensure you have a suitable development environment set up.
2. **Project Initialization**: Create a new Python project and import necessary modules from 'ai-dev-browser'. Initialize the browser instance.
3. **Navigating Websites**: Write functions to navigate to different URLs and handle redirections automatically. Implement a feature to log the navigation history.
4. **Web Interaction**: Develop functionalities to interact with web elements such as input fields, buttons, and links. Use the 'ai-dev-browser' package's capabilities to simulate user interactions.
5. **Form Handling**: Include a form-filling feature where users can provide form data, and the application fills out web forms automatically. Handle various types of form inputs including dropdowns, checkboxes, and file uploads.
6. **Scrolling and Scrolling Detection**: Automate scrolling actions and implement a detection mechanism to identify when all content has been loaded.
7. **Error Handling and Logging**: Implement robust error handling to manage unexpected issues such as network failures or unresponsive sites. Log errors and user interactions for debugging purposes.
8. **User Interface**: Design a simple command-line interface (CLI) for users to control the application. Users should be able to enter commands to navigate, fill forms, and perform other actions.
9. **Testing and Documentation**: Test the application thoroughly to ensure it works as expected across multiple websites. Document the code and provide usage instructions.

The goal is to create a versatile tool that can automate repetitive web tasks while providing a smooth user experience.