argentor-sdk

v1.4.7 safe
3.0
Low Risk

Python SDK client for the Argentor AI agent framework REST API

🤖 AI Analysis

Final verdict: SAFE

The package appears to be a legitimate Python SDK for interacting with the Argentor AI agent framework's REST API. There are no indications of malicious activities such as shell execution, obfuscation, or credential harvesting.

  • Standard usage of httpx for network requests.
  • No signs of obfuscation or credential harvesting.
Per-check LLM notes
  • Network: The use of httpx for making network requests is common and expected in many packages, suggesting standard API interaction rather than malicious intent.
  • Shell: No shell execution patterns detected, indicating no risk associated with direct system command execution.
  • Obfuscation: No obfuscation patterns detected, indicating low risk.
  • Credentials: No credential harvesting patterns detected, indicating low risk.
  • Metadata: The author has only one package, suggesting a new or less active account which could indicate potential risk but lacks clear evidence of malicious intent.

📦 Package Quality Overall: Medium (5.8/10)

◈ Medium Test Suite 6.0

Partial test coverage signals detected

  • 2 test file(s) detected (e.g. test_client.py)
◈ Medium Documentation 7.0

Some documentation present

  • Documentation URL: "Documentation" -> https://github.com/fboiero/Agentor/tree/master/sdks/python
  • Detailed PyPI description (6330 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

  • Classifier: Typing :: Typed
  • 51 type-annotated function signatures detected in source
◈ Medium Multiple Contributors 5.0

Limited contributor diversity

  • 1 unique contributor(s) across 100 commits in fboiero/Agentor
  • Single author but highly active (100 commits)

🔬 Heuristic Checks

⚠ Outbound Network Calls score 6.0

Found 4 network call pattern(s)

  • try: self._http = httpx.Client( base_url=self.base_url, hea
  • nant_id) self._http = httpx.AsyncClient( base_url=self.base_url, headers=sel
  • s. Usage:: with httpx.Client() as http: with http.stream("POST", url, json=pa
  • Usage:: async with httpx.AsyncClient() as http: async with http.stream("POST", url, j
✓ 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

No author email provided

✓ Suspicious Page Links

All external links appear legitimate

✓ Git Repository History

Repository fboiero/Agentor appears legitimate

⚠ Maintainer History score 2.0

1 maintainer concern(s) found

  • Author "Argentor Contributors" 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 argentor-sdk 
Create a command-line utility named 'ArgentorAgentCLI' using the Python package 'argentor-sdk'. This tool will serve as an interface for users to interact with their Argentor AI agents through a series of commands. Your task is to implement several key functionalities that showcase the capabilities of the Argentor AI agent framework.

Step 1: Initialize your project by setting up a virtual environment and installing the required packages, including 'argentor-sdk'.

Step 2: Design and implement the following commands within 'ArgentorAgentCLI':
- 'list-agents': List all available AI agents managed by the user.
- 'create-agent': Create a new AI agent with specified parameters such as name, description, and type.
- 'delete-agent': Delete an existing AI agent by its unique identifier.
- 'get-agent': Retrieve detailed information about a specific AI agent.
- 'train-agent': Train an AI agent with custom data or configurations.
- 'run-task': Execute a predefined task using an AI agent and display the results.

Step 3: Ensure each command accepts appropriate input arguments and outputs clear, informative messages.

Step 4: Write unit tests to validate the functionality of your CLI tool, covering all implemented commands.

Step 5: Document your project thoroughly, explaining how to install, configure, and use 'ArgentorAgentCLI', including examples of common workflows.

In this project, you will utilize the 'argentor-sdk' package extensively to interact with the Argentor AI agent framework's REST API. This includes making HTTP requests to create, retrieve, update, and delete AI agents, as well as executing tasks on these agents. Your goal is to demonstrate a seamless integration between the CLI and the Argentor framework, providing a powerful yet easy-to-use interface for managing AI agents.