adjacency-agents

v0.1.1 safe
4.0
Medium Risk

Deterministic tool orchestration for LLM/SLM flows with policy-gated parsing.

🤖 AI Analysis

Final verdict: SAFE

The package exhibits minimal risk based on the checks performed. It does not engage in network calls, shell executions, or obfuscation techniques, and there is no evidence of credential harvesting.

  • Low risk in all categories except metadata.
  • Anonymous author and low community engagement raise minor concerns.
Per-check LLM notes
  • Network: No network calls detected, which is normal if the package does not require external communications.
  • Shell: No shell execution patterns detected, indicating the package likely does not execute system commands.
  • 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 anonymous author and lack of community engagement, but no clear signs of typosquatting or other malicious intent.

🔬 Heuristic Checks

Outbound Network Calls

No suspicious network call patterns found

Code Obfuscation

No obfuscation patterns detected

Shell / Subprocess Execution

No shell execution patterns detected

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 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 adjacency-agents
Create a fully-functional mini-application called 'PolicyGuardian' that leverages the 'adjacency-agents' package to manage and enforce policies over a series of deterministic tool orchestrations within a machine learning workflow. The application will serve as a robust framework for ensuring that each step in the workflow adheres strictly to predefined rules and conditions before proceeding to the next stage. Here's a detailed breakdown of the application's requirements and functionalities:

1. **Workflow Definition**: Users should be able to define their own workflows consisting of multiple steps or tools. Each step can be any command-line tool or script.
2. **Policy Creation**: Policies should be defined for each step, specifying conditions under which the step can proceed. For example, a step might require that the output from the previous step meets certain criteria before it can execute.
3. **Execution Orchestration**: The application should use 'adjacency-agents' to ensure that each step executes only if all its policy conditions are met. This involves parsing the output of one tool to determine if the next tool can run.
4. **Monitoring & Reporting**: Provide real-time monitoring of the workflow execution status, including logs and reports on whether each policy was successfully enforced.
5. **User Interface**: Develop a simple web interface using Flask or Django where users can input their workflows, define policies, and monitor the execution status.
6. **Scalability**: Ensure the application is scalable, allowing for the addition of more tools and complex workflows without significant performance degradation.
7. **Error Handling**: Implement robust error handling to manage scenarios where policies cannot be satisfied, such as providing alternative paths or notifying the user.

The 'adjacency-agents' package will be central to enforcing the policies between steps. It will handle the parsing of outputs and decision-making on whether to proceed based on the defined policies. This project aims to showcase the power of deterministic tool orchestration in machine learning workflows, ensuring reliability and adherence to business logic throughout the process.