agent-cli

v0.99.0 suspicious
4.0
Medium Risk

A suite of AI-powered command-line tools for text correction, audio transcription, and voice assistance.

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package has moderate risks due to shell execution and network activities, although there is no clear evidence of malicious intent. The low maintainer engagement and presence of non-secure links increase suspicion.

  • Moderate shell risk
  • Potential for insecure network calls
  • Low maintainer engagement
Per-check LLM notes
  • Network: Network calls appear to be related to downloading resources and making HTTP requests, which could be legitimate depending on the package's functionality.
  • Shell: Shell execution patterns may indicate that the package runs external commands, potentially posing a risk if these commands are not securely controlled or can be manipulated.
  • Obfuscation: No obfuscation patterns detected, indicating low risk of malicious activity related to code obfuscation.
  • Credentials: No credential harvesting patterns detected, indicating low risk of malicious activity related to stealing secrets.
  • Metadata: The package shows low maintainer engagement and includes non-secure links, raising some suspicion but not conclusive evidence of malice.

🔬 Heuristic Checks

⚠ Outbound Network Calls score 6.0

Found 4 network call pattern(s)

  • # Download with progress urllib.request.urlretrieve(SILERO_VAD_URL, SILERO_VAD_CACHE) # noqa: S310
  • est.body() async with httpx.AsyncClient(timeout=60.0) as http: req = http.build_request(
  • nc with ( httpx.AsyncClient(timeout=120.0) as client, client.stream(
  • vent-stream") async with httpx.AsyncClient(timeout=120.0) as client: response = await client.po
✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 10.0

Found 6 shell execution pattern(s)

  • ), ] result = subprocess.run(cmd, check=False, capture_output=True) if result.ret
  • """ try: result = subprocess.run( code.split(), capture_output=True,
  • per.Exit(1) try: subprocess.run([*editor_cmd, str(config_file)], check=True) except File
  • str(output_wav), ] subprocess.run(cmd, check=True) def build_retranscribe_request( optio
  • t(start * 1000):08d}.wav" subprocess.run( [ ffmpeg, "-y",
  • nd-line player.""" return subprocess.Popen( _audio_player_command(player, audio_path),
✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: nijho.lt>

⚠ Suspicious Page Links score 4.0

Found 2 suspicious link(s) on the package page

  • Non-HTTPS external link: http://img.youtube.com/vi/7sBTCgttH48/0.jpg
  • Non-HTTPS external link: http://www.youtube.com/watch?v=7sBTCgttH48
✓ Git Repository History

Repository basnijholt/agent-cli appears legitimate

⚠ Maintainer History score 6.0

3 maintainer concern(s) found

  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
  • Package has no PyPI classifiers (low effort / metadata quality)
✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with agent-cli 
Create a comprehensive personal assistant command-line application using the 'agent-cli' Python package. This app will serve as a versatile tool for managing daily tasks, enhancing productivity, and integrating AI-driven functionalities into your workflow. Here's a detailed breakdown of the project requirements and steps:

1. **Project Overview**: Design a CLI-based personal assistant named 'AI-Personal-Helper'. It should leverage 'agent-cli' to provide text correction, audio transcription, and voice assistance features.
2. **Features**:
   - **Text Correction Tool**: Allow users to input text and receive corrections for spelling, grammar, and style. Utilize 'agent-cli' for real-time text analysis and suggestions.
   - **Audio Transcription Module**: Integrate a feature where users can upload audio files and get them transcribed into text. Use 'agent-cli' for speech recognition and conversion.
   - **Voice Assistance Feature**: Enable users to interact with the assistant through voice commands. Implement 'agent-cli' for voice recognition and response generation.
3. **User Interface**: Design a user-friendly CLI interface that clearly outlines available commands and functionalities. Ensure ease of navigation between different features.
4. **Implementation Steps**:
   - **Setup Environment**: Install necessary Python packages including 'agent-cli', and configure the environment to support text processing and audio handling.
   - **Develop Text Correction Tool**: Write functions to accept user input, utilize 'agent-cli' for text correction, and display results back to the user.
   - **Implement Audio Transcription**: Develop functionality to accept audio file inputs, process them with 'agent-cli' for transcription, and output the text result.
   - **Add Voice Commands Support**: Incorporate voice recognition capabilities allowing users to give voice commands which 'agent-cli' processes to perform actions like initiating text correction or transcription.
5. **Testing**: Thoroughly test each feature to ensure accuracy and reliability. Focus on edge cases such as handling different accents in voice commands or unusual text inputs.
6. **Documentation**: Provide clear documentation on how to install, use, and customize 'AI-Personal-Helper'. Include examples of common use cases and troubleshooting tips.
7. **Deployment**: Prepare the application for deployment by packaging it into a distributable format and uploading it to a repository for easy access.

By following these guidelines, you'll create a robust and user-friendly personal assistant application that effectively integrates AI capabilities through 'agent-cli', enhancing user interaction and productivity.