ai-agent-lab

v0.2.0 suspicious
5.0
Medium Risk

Python toolkit for building AI agent systems with Claude Code — MCP servers, orchestration, skills, and hooks

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package has a moderate risk score due to shell execution risk and uncertain metadata, suggesting potential issues but lacking clear evidence of malicious intent.

  • Shell execution risk detected
  • Uncertain metadata and maintainer history
Per-check LLM notes
  • Network: No network calls detected, which is low risk.
  • Shell: Shell execution to run a local server script might be legitimate but requires verification of the package's intended functionality.
  • Metadata: The repository's recent activity pattern and maintainer history suggest potential risk, though not conclusive evidence of malice.

📦 Package Quality Overall: Low (4.6/10)

✦ High Test Suite 9.0

Test suite present — 4 test file(s) found

  • Test runner config found: pyproject.toml
  • 4 test file(s) detected (e.g. test_server.py)
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (9087 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

  • 34 type-annotated function signatures detected in source
○ Low Multiple Contributors 2.0

Single-author or unverifiable project

  • 1 unique contributor(s) across 7 commits in Akkikens/agent-lab
  • Single author with few commits — possibly a personal or throwaway project

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 4.0

Found 2 shell execution pattern(s)

  • s_file.unlink() result = subprocess.run( ["uv", "run", "python", "server.py"], input
  • + "\\n" result = subprocess.run( ["uv", "run", "python", "server.py"],
✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: gmail.com>

✓ Suspicious Page Links

All external links appear legitimate

⚠ Git Repository History score 5.0

Git history flags: Repository has zero stars and zero forks

  • Repository has zero stars and zero forks
  • All 7 commits happened within 24 hours
⚠ 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 ai-agent-lab 
Create a mini-application called 'SmartTaskMaster' using the Python package 'ai-agent-lab'. This application will serve as a personal task management system that leverages AI agents to help users manage their daily tasks more efficiently. Here are the key functionalities of SmartTaskMaster:

1. **User Interface**: Develop a simple command-line interface (CLI) where users can interact with the application.
2. **Task Management**: Users should be able to add new tasks, view their current tasks, mark tasks as completed, and delete tasks.
3. **AI Agent Integration**: Utilize the 'ai-agent-lab' package to create an AI agent that monitors the user's task list and suggests optimal times to complete tasks based on the user's activity patterns.
4. **Activity Patterns Learning**: The AI agent should learn from the user's behavior over time to better predict the best times for task completion.
5. **Notifications**: Implement a feature where the AI agent sends notifications to remind users about upcoming deadlines or suggest starting a task.
6. **Customizable Skills**: Allow users to customize the AI agent's skills, such as adjusting reminder times or setting priority levels for different types of tasks.
7. **Logging and Reporting**: Include logging functionality to track the performance of the AI agent and reporting tools to analyze task completion trends.

To achieve these functionalities, you'll need to leverage several components of the 'ai-agent-lab' package:
- Use Claude Code — MCP servers to handle the backend operations of the AI agent.
- Employ orchestration capabilities to manage the workflow of task management and AI suggestions.
- Integrate skills to enable the AI agent to perform specific actions like sending reminders or analyzing task data.
- Implement hooks to ensure seamless interaction between the CLI and the AI agent's actions.

Your goal is to build a fully functional, user-friendly task management tool that demonstrates the power of integrating AI into everyday applications.