🤖 AI Analysis

Final verdict: SAFE

The package agentpeek v0.13.0 exhibits low risks across network, shell, obfuscation, and credential fronts. The metadata risk is moderately elevated due to potential account irregularities, but there's no concrete evidence of malicious behavior.

Shell risk requires close monitoring due to potential misuse.
Metadata suggests a new or inactive account, raising minor suspicion.

Per-check LLM notes

Network: No network calls detected, which is normal and not indicative of malicious activity.
Shell: Shell execution appears to be for legitimate purposes like editing files and managing system processes, but requires careful review to ensure commands are not being abused.
Obfuscation: No obfuscation patterns detected, indicating low risk.
Credentials: No credential harvesting patterns detected, indicating low risk.
Metadata: The package shows some red flags such as an author with a missing or short name and a new or inactive account, but no direct evidence of malicious intent.

📦 Package Quality Overall: Medium (5.0/10)

◈ Medium Test Suite 6.0

Partial test coverage signals detected

Test runner config found: pyproject.toml

◈ Medium Documentation 5.0

Some documentation present

Detailed PyPI description (5244 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 7.0

Partial type annotation coverage

Classifier: Typing :: Typed
161 type-annotated function signatures detected in source

◈ Medium Multiple Contributors 5.0

Limited contributor diversity

1 unique contributor(s) across 100 commits in rattle99/agentpeek
Single author but highly active (100 commits)

🔬 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)

nic() try: proc = subprocess.run( # noqa: S603 - cmd is built from a fixed allowlist
th app.suspend(): subprocess.run([editor, str(path)], check=False) async def action_refr

✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: users.noreply.github.com>

✓ Suspicious Page Links

All external links appear legitimate

⚠ Git Repository History score 2.5

Git history flags: Repository has zero stars and zero forks

Repository has zero stars and zero forks

⚠ 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 agentpeek

Your task is to create a user-friendly command-line tool called 'AgentInspector' using Python and the 'agentpeek' package. This tool will serve as a visual interface for users to explore and manage their agent CLI configuration files stored in directories such as ~/.claude/. Here’s a detailed breakdown of what your application should accomplish:

1. **Setup and Installation**: Ensure your application includes a setup.py file for easy installation via pip. Users should be able to install AgentInspector and have it ready to use right away.

2. **Main Features**:
- **Directory Navigation**: Allow users to navigate through different agent configuration directories easily. This could include listing all available directories and providing options to switch between them.
- **Configuration File Inspection**: Implement a feature where users can inspect individual configuration files within the selected directory. Display the contents of these files in a readable format.
- **Search Functionality**: Integrate a search function that allows users to find specific settings or values within the configuration files.
- **Editing Capabilities**: Provide basic editing capabilities so users can modify settings directly from the tool. Ensure changes are saved automatically.
- **Help Documentation**: Include comprehensive help documentation accessible via a command or menu option. This should cover common tasks and troubleshooting tips.

3. **Utilization of 'agentpeek' Package**: Use the 'agentpeek' package to facilitate the inspection and navigation of the configuration directories. Specifically, leverage its TUI (Text User Interface) capabilities to present information in an organized and interactive manner.

4. **Enhanced User Experience**: Aim to make the user experience as smooth as possible. Consider adding features like keyboard shortcuts, context-sensitive help, and a clean, intuitive UI design.

5. **Testing and Validation**: Before finalizing your project, ensure thorough testing of all functionalities. Write unit tests for critical components and perform manual testing to catch any potential bugs or usability issues.

6. **Documentation and Deployment**: Prepare a README file detailing how to install, configure, and use AgentInspector. Additionally, consider deploying your application on a platform like GitHub so others can contribute or download it.

By following these guidelines, you'll develop a robust and user-friendly tool that enhances the management of agent configurations.