agnt

v0.13.15 suspicious
6.0
Medium Risk

MCP server for AI coding agents - process management, reverse proxy with traffic logging, browser instrumentation, and sketch mode

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package shows high risk for shell execution and moderate risk for network calls, which together suggest potential misuse. However, there is no direct evidence of malicious activity.

  • High shell risk indicating potential for executing unauthorized commands
  • Moderate network risk suggesting possible data exfiltration
Per-check LLM notes
  • Network: The network call pattern suggests the package may be making external requests which could be used for legitimate purposes like fetching updates, but also poses a risk for potential data exfiltration.
  • Shell: Executing arbitrary binaries and system arguments directly from user input is highly risky and can indicate a backdoor or a way to execute unauthorized commands on the host machine.
  • Obfuscation: No obfuscation patterns detected, indicating low risk.
  • Credentials: No credential harvesting patterns detected, indicating low risk.
  • Metadata: The maintainer has a new or inactive account with limited package history and lacks author details, raising some suspicion but not conclusive evidence of malice.

📦 Package Quality Overall: Low (3.8/10)

○ Low Test Suite 1.0

No test suite detected

  • No test files or test-runner configuration detected
◈ Medium Documentation 7.0

Some documentation present

  • Documentation URL: "Documentation" -> https://standardbeagle.github.io/agnt/
  • Detailed PyPI description (3343 chars)
○ Low Contributing Guide 4.0

No contributing guide or governance files found

  • Development Status classifier >= Beta
○ Low Type Annotations 1.0

No type annotations detected

  • No type annotations, py.typed marker, or stub files detected
◈ Medium Multiple Contributors 6.0

Limited contributor diversity

  • 2 unique contributor(s) across 100 commits in standardbeagle/agnt
  • Two distinct contributors found

🔬 Heuristic Checks

⚠ Outbound Network Calls score 1.5

Found 1 network call pattern(s)

  • tderr) try: with httpx.Client(follow_redirects=True, timeout=60.0) as client:
✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 4.0

Found 2 shell execution pattern(s)

  • get_binary_path() return subprocess.run([str(binary_path)] + (args or [])) def main() -> None:
  • bprocess result = subprocess.run([str(binary_path)] + sys.argv[1:]) sys.exit(resu
✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: standardbeagle.com>

✓ Suspicious Page Links

All external links appear legitimate

✓ Git Repository History

Repository standardbeagle/agnt appears legitimate

⚠ 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 agnt 
Create a web-based code editor application called 'CodeCraft' that leverages the 'agnt' package to enhance developer productivity. CodeCraft will serve as a versatile platform where developers can write, test, and run their code snippets directly within the browser. It will include several advanced features such as real-time collaboration, syntax highlighting, and integrated terminal access. Additionally, CodeCraft will utilize 'agnt' to manage processes, log traffic, and instrument the browser for enhanced user experience.

Here’s how you can structure the application:
1. **Setup Environment**: Begin by installing the necessary packages including 'agnt'. Ensure that the environment is set up to support real-time interaction between the client and server.
2. **Real-Time Collaboration**: Implement a feature where multiple users can edit the same code snippet simultaneously. This feature should highlight changes made by different users in real-time.
3. **Syntax Highlighting**: Integrate syntax highlighting for various programming languages supported by your application. Use 'agnt' to reverse proxy requests to language-specific servers for processing.
4. **Integrated Terminal Access**: Provide an integrated terminal within the editor where users can execute their code snippets directly from the editor. Use 'agnt' to manage these terminal sessions efficiently.
5. **Browser Instrumentation**: Utilize 'agnt' to instrument the browser, enhancing the performance and responsiveness of CodeCraft. This includes optimizing network requests and handling large datasets more efficiently.
6. **Sketch Mode**: Implement a sketch mode using 'agnt', allowing users to quickly jot down ideas and pseudocode without worrying about syntax. This mode should seamlessly transition into full editing mode when the user is ready to write actual code.
7. **Traffic Logging**: Enable detailed logging of all interactions within CodeCraft. Use 'agnt' to manage and analyze this data, providing insights into user behavior and application performance.
8. **Testing and Debugging Tools**: Incorporate basic testing and debugging tools directly within the editor. These tools should allow users to run tests and debug code without leaving the editor interface.

Your task is to design and implement these features using Python and the 'agnt' package. Focus on creating a seamless and efficient user experience while showcasing the capabilities of 'agnt'.