agentyc

v0.3.3 suspicious
5.0
Medium Risk

Deterministic MCP-first browser automation runtime for coding agents

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package has moderate risks due to potential unauthorized data collection through shell commands and network activity that may download external files.

  • Shell commands execution raises concerns about unauthorized data collection.
  • Network calls suggest possible download of external files which could introduce additional risks.
Per-check LLM notes
  • Network: The network calls appear to be for downloading files, which could be legitimate if the package requires external resources.
  • Shell: Executing git commands suggests the package might be collecting version control information, but it raises concern as unauthorized data collection or exfiltration could occur.

📦 Package Quality Overall: Medium (6.0/10)

◈ Medium Test Suite 6.0

Partial test coverage signals detected

  • Test runner config found: pyproject.toml
◈ Medium Documentation 7.0

Some documentation present

  • Documentation URL: "Documentation" -> https://github.com/distillation-labs/agentyc/tree/main/docs
  • Detailed PyPI description (22211 chars)
○ Low Contributing Guide 4.0

No contributing guide or governance files found

  • Development Status classifier >= Beta
◈ Medium Type Annotations 7.0

Partial type annotation coverage

  • Type checker (mypy / pyright / pytype) referenced in project
  • 251 type-annotated function signatures detected in source
◈ Medium Multiple Contributors 6.0

Limited contributor diversity

  • 2 unique contributor(s) across 100 commits in distillation-labs/agentyc
  • Two distinct contributors found

🔬 Heuristic Checks

⚠ Outbound Network Calls score 4.5

Found 3 network call pattern(s)

  • on .crx file.""" try: with urllib.request.urlopen(url) as response: with open(output_path, 'wb') as
  • nously.""" try: async with httpx.AsyncClient(timeout=3.0) as client: response = await client.get('http
  • 7.0.0.1', '::1') async with httpx.AsyncClient(timeout=httpx.Timeout(30.0), trust_env=not is_localhost) as
⚠ Code Obfuscation score 4.0

Found 2 obfuscation pattern(s)

  • creenshot screenshot_data = base64.b64decode(screenshot_b64) image = Image.open(io.BytesIO(screenshot_d
  • ame, 'wb') as f: f.write(base64.b64decode(final_screenshot)) logger.debug('Saved screenshot to ' +
⚠ Shell / Subprocess Execution score 10.0

Found 6 shell execution pattern(s)

  • rn None commit_hash = ( subprocess.check_output(['git', 'rev-parse', 'HEAD'], cwd=package_root, stderr=subpr
  • ).strip() ) branch = ( subprocess.check_output(['git', 'rev-parse', '--abbrev-ref', 'HEAD'], cwd=package_ro
  • rip() ) remote_url = ( subprocess.check_output(['git', 'config', '--get', 'remote.origin.url'], cwd=package
  • ) commit_timestamp = ( subprocess.check_output(['git', 'show', '-s', '--format=%ci', 'HEAD'], cwd=package_r
  • '--label', label]) result = subprocess.run(command, check=False, capture_output=True, text=True) if re
  • owser']: try: result = subprocess.run(['which', cmd], capture_output=True, text=True) if resul
✓ 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 distillation-labs/agentyc appears legitimate

⚠ Maintainer History score 2.0

1 maintainer concern(s) found

  • Author "Japneet Kalkat" 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 agentyc 
Create a web-based task automation tool named 'WebTaskMaster' using the Python package 'agentyc'. This tool will allow users to schedule and automate repetitive tasks on websites, such as form submissions, data scraping, and interactive element manipulation. The goal is to provide a user-friendly interface where non-technical users can define tasks through a simple configuration file or UI without needing to write code.

### Features:
1. **Task Configuration Interface**: Develop a web interface where users can input details of their tasks, including URL, actions to perform (e.g., clicking buttons, filling forms), and timing schedules.
2. **Task Execution Engine**: Utilize 'agentyc' to create deterministic and reliable task execution workflows. Ensure each task runs exactly as specified without unexpected variations.
3. **Real-Time Monitoring**: Implement a dashboard to monitor the status of scheduled tasks, showing progress, completion times, and any errors encountered during execution.
4. **Task History Log**: Maintain a log of all executed tasks, including outcomes and timestamps, for auditing purposes.
5. **User Authentication & Role Management**: Secure the application with user authentication and role-based access control, allowing administrators to manage multiple user accounts and their respective task permissions.
6. **Customizable Notifications**: Allow users to set up notifications (via email or SMS) when a task completes or fails.
7. **Integration with External Services**: Enable integration with external services like email providers for sending notifications or database systems for storing scraped data.

### Steps to Build:
1. **Setup Project Environment**: Initialize a new Python project and install necessary dependencies, including 'agentyc', Flask for the web framework, SQLAlchemy for ORM, and any other required packages.
2. **Design Database Schema**: Define the database schema to store user information, task configurations, and execution logs.
3. **Develop Web Interface**: Use Flask to create a responsive frontend for task configuration and monitoring.
4. **Implement Task Execution Logic**: Write the backend logic to interpret task configurations and execute them using 'agentyc'. Pay special attention to error handling and ensuring tasks run deterministically.
5. **Add Real-Time Monitoring and Logging**: Integrate real-time monitoring capabilities and logging functionalities to track task execution statuses.
6. **Secure the Application**: Implement user authentication and role management to secure the application.
7. **Test Thoroughly**: Conduct extensive testing to ensure all features work as expected and that 'agentyc' is being utilized correctly for task automation.
8. **Deploy**: Deploy the application to a cloud service provider like AWS or Heroku, making sure to configure environment variables and security settings properly.