agentic-graphs

v0.2.2 suspicious
4.0
Medium Risk

Graph-native framework for building AI agents with FalkorDB persistence

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package exhibits moderate risk due to high obfuscation risk and medium metadata risk, despite having no evident network, shell execution, or credential risks.

  • High obfuscation risk due to the use of eval with restricted builtins
  • Medium metadata risk due to low popularity and recent repository activity
Per-check LLM notes
  • Network: The use of asynchronous HTTP requests is common for fetching remote resources and does not inherently suggest malicious intent.
  • Shell: No shell execution patterns were detected.
  • Obfuscation: The use of eval with restricted builtins suggests potential for code injection and obfuscation.
  • Credentials: No direct evidence of credential harvesting is present.
  • Metadata: The repository's recent activity and low popularity suggest potential risk.

🔬 Heuristic Checks

⚠ Outbound Network Calls score 4.5

Found 3 network call pattern(s)

  • st[float]: async with httpx.AsyncClient(timeout=self._timeout) as client: r = await clie
  • ] = tools async with httpx.AsyncClient(timeout=self._timeout) as client: r = await clie
  • ] = tools async with httpx.AsyncClient(timeout=self._timeout) as client: async with cli
⚠ Code Obfuscation score 2.0

Found 1 obfuscation pattern(s)

  • " try: return str(eval(expr, {"__builtins__": {}}, {})) except Exception as e:
✓ Shell / Subprocess Execution

No shell execution patterns detected

✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

No author email provided

✓ 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 2.0

1 maintainer concern(s) found

  • Author "Agentic Graphs Contributors" 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 agentic-graphs 
Create a small, fully-functional mini-application that leverages the 'agentic-graphs' package to manage a network of interconnected AI agents. Each agent in this network represents a character from a popular book series, such as Harry Potter. These characters will interact with each other based on predefined rules and events, simulating a dynamic social network. Here’s a step-by-step guide to building this application:

1. **Setup Environment**: Begin by setting up your Python environment. Ensure you have the latest version of Python installed along with the necessary dependencies, including the 'agentic-graphs' package.

2. **Define Characters**: Create a class or structure to define each character in the network. Include attributes such as name, role, relationships (friends/enemies), and unique abilities or traits.

3. **Graph Construction**: Use 'agentic-graphs' to construct a graph where nodes represent characters and edges represent their relationships. Utilize FalkorDB for persistence to ensure the graph remains consistent across sessions.

4. **Event Handling**: Implement a system where random or user-defined events trigger interactions between characters. For example, a new event could cause a friendship to form or an enemy to be made.

5. **AI Agents Interaction**: Design simple AI agents using 'agentic-graphs' to simulate decision-making processes for each character. Agents should be able to navigate the graph to find friends, enemies, or other characters based on their current status and goals.

6. **Visualization**: Integrate a visualization tool (such as D3.js or a Python library like NetworkX) to display the evolving social network in real-time.

7. **User Interface**: Develop a basic web interface where users can add new characters, modify relationships, and trigger events manually.

8. **Testing and Debugging**: Thoroughly test the application to ensure all components work correctly together. Pay special attention to how the graph evolves over time and how persistent data is handled through FalkorDB.

9. **Documentation**: Write clear documentation detailing how to install, run, and extend the application. Include examples of how to create new characters, modify the graph, and implement custom events.

This project not only showcases the power of 'agentic-graphs' for managing complex networks but also demonstrates its potential for creating interactive, dynamic systems.