agentmesh_discovery

v4.0.0 suspicious
6.0
Medium Risk

Shadow AI agent discovery and inventory for the Agent Governance Toolkit

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package exhibits a moderate level of risk due to its execution of shell commands and incomplete maintainer metadata, which could indicate potential misuse or unauthorized access.

  • High shell risk from executing potentially dangerous commands.
  • Incomplete maintainer metadata raises concerns about package origin and intent.
Per-check LLM notes
  • Network: Making network calls to GitHub API is common and usually benign, but the context of use should be verified.
  • Shell: Executing shell commands like 'wmic' and 'ps aux' can be used for legitimate purposes such as process monitoring, but also indicate potential risk for unauthorized access or system manipulation.
  • Obfuscation: Base64 decoding is commonly used for data serialization and not necessarily indicative of malicious activity.
  • Credentials: Direct access to environment variables for tokens can pose risks if not handled securely; this may indicate a need for better credential management practices.
  • Metadata: The maintainer has an incomplete profile and seems to be new or inactive, raising some suspicion.

📦 Package Quality Overall: Medium (6.6/10)

✦ High Test Suite 9.0

Test suite present — 6 test file(s) found

  • Test runner config found: pyproject.toml
  • 6 test file(s) detected (e.g. test_cli.py)
◈ Medium Documentation 7.0

Some documentation present

  • Documentation URL: "Documentation" -> https://github.com/microsoft/agent-governance-toolkit/tree/m
  • Detailed PyPI description (10134 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

  • 35 type-annotated function signatures detected in source
✦ High Multiple Contributors 10.0

Active multi-contributor project

  • 14 unique contributor(s) across 100 commits in microsoft/agent-governance-toolkit
  • Active community — 5 or more distinct contributors

🔬 Heuristic Checks

⚠ Outbound Network Calls score 1.5

Found 1 network call pattern(s)

  • {token}" async with httpx.AsyncClient( base_url="https://api.github.com",
⚠ Code Obfuscation score 2.0

Found 1 obfuscation pattern(s)

  • ue content = base64.b64decode(resp.json().get("content", "")).decode(
⚠ Shell / Subprocess Execution score 4.0

Found 2 shell execution pattern(s)

  • """ try: result = subprocess.run( ["wmic", "process", "get", "ProcessId,CommandLi
  • """ try: result = subprocess.run( ["ps", "aux"], # noqa: S607 — known CLI tool p
⚠ Credential Harvesting score 2.5

Found 1 credential access pattern(s)

  • oken = kwargs.get("token") or os.environ.get("GITHUB_TOKEN", "") repos: list[str] = kwargs.get("repos", [])
✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: microsoft.com>

✓ Suspicious Page Links

All external links appear legitimate

✓ Git Repository History

Repository microsoft/agent-governance-toolkit 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 agentmesh_discovery 
Create a Shadow AI Agent Inventory Manager using the 'agentmesh_discovery' Python package. This tool will serve as a central hub for managing and monitoring Shadow AI agents within an organization. Your task is to design and implement a command-line interface (CLI) application that leverages the capabilities of 'agentmesh_discovery' to discover, manage, and report on Shadow AI agents.

Step 1: Setup your development environment by installing the necessary packages including 'agentmesh_discovery'. Ensure you have Python installed and set up a virtual environment for this project.

Step 2: Define the core functionalities of your application:
- Discover Shadow AI agents across different networks.
- Retrieve detailed information about each discovered agent, such as its status, location, and capabilities.
- Allow users to filter and search through the inventory based on specific criteria like agent type, network location, etc.
- Provide options to mark agents as active/inactive or update their metadata.

Step 3: Utilize 'agentmesh_discovery' to integrate these functionalities into your application. Use its API to query and interact with Shadow AI agents.

Step 4: Implement a user-friendly CLI that guides users through the process of discovering, managing, and reporting on Shadow AI agents. Include clear commands and help messages.

Step 5: Enhance the application by adding additional features such as:
- Automated health checks for agents.
- Notifications for critical events related to agents (e.g., failure to connect).
- Integration with external tools or platforms for extended functionality.

Your final product should demonstrate proficiency in using 'agentmesh_discovery' and provide a robust solution for managing Shadow AI agents.