🤖 AI Analysis

Final verdict: SUSPICIOUS

The package shows some potential red flags, particularly concerning metadata and shell execution risks, but lacks clear indicators of malicious behavior.

Metadata risk due to recent repository creation, low activity, and single contributor.
Shell execution risk due to use of 'subprocess.run' with 'shell=True'.

Per-check LLM notes

Network: No network calls detected, which is neutral from a risk perspective.
Shell: Shell execution with 'subprocess.run' and 'shell=True' can introduce risks if the commands executed are not controlled or sanitized, potentially leading to security vulnerabilities.
Obfuscation: No obfuscation patterns detected, indicating low risk of malicious obfuscation.
Credentials: No credential harvesting patterns detected, indicating low risk of credential theft.
Metadata: The repository and maintainer history indicate potential red flags such as recent creation, low activity, and single contributor, suggesting possible malicious intent.

📦 Package Quality Overall: Medium (5.4/10)

✦ High Test Suite 9.0

Test suite present — 15 test file(s) found

Test runner config found: pyproject.toml
15 test file(s) detected (e.g. test_agent_consumer.py)

◈ Medium Documentation 5.0

Some documentation present

Detailed PyPI description (10404 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
163 type-annotated function signatures detected in source

○ Low Multiple Contributors 2.0

Single-author or unverifiable project

1 unique contributor(s) across 1 commits in abrahamjunzou/agentwright
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)

try: proc = subprocess.run( command, shell=True,
command, shell=True, cwd=str(work), capture_out

✓ 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 10.0

Git history flags: Repository created very recently: 4 day(s) ago (2026-06-02T00:55:48Z)

Repository created very recently: 4 day(s) ago (2026-06-02T00:55:48Z)
Repository has zero stars and zero forks
Very few commits: 1 total
Single contributor with only 1 commit(s) — possibly throwaway account

⚠ Maintainer History score 6.0

3 maintainer concern(s) found

Only one version has ever been released — brand new package
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 agentwright

Your task is to develop a mini-application that helps users manage and validate simple AI agents using the 'agentwright' Python package. This tool will allow users to define, validate, and run AI agents with ease. Here’s a step-by-step guide on what your application should do:

1. **Setup**: Ensure your environment is set up correctly with all necessary packages installed, including 'agentwright'.
2. **Agent Definition**: Allow users to define their own AI agents through a user-friendly interface or configuration file. Each agent should have specific attributes like name, description, input/output types, etc.
3. **Validation**: Implement a feature to validate the defined agents based on the rules provided by 'agentwright'. This ensures that each agent meets certain criteria before it can be run.
4. **Execution**: Once validated, provide functionality to execute these agents. Users should be able to see the output of the agents they've created or imported.
5. **Results Visualization**: Offer a way to visualize the results of the executed agents, such as graphs or tables, to help users understand the performance of their agents better.
6. **Documentation & Help**: Include comprehensive documentation and a help section to guide users through the process of defining, validating, and running agents.

**Suggested Features**:
- Support for multiple agent definitions within a single project.
- Integration with popular machine learning frameworks to enhance agent capabilities.
- Real-time validation feedback during agent definition.
- Export/import functionalities for agent definitions.
- User-friendly GUI or CLI options for interaction.

**How to Utilize 'agentwright'**:
- Use 'agentwright' to define the structure and types of your agents.
- Leverage its validation capabilities to ensure that the agents meet the specified criteria.
- Employ 'agentwright' to run and manage the execution of the agents.

By following these guidelines, you'll create a powerful yet easy-to-use tool for managing AI agents.