agentguard-kernel

v0.1.0 suspicious
4.0
Medium Risk

Constitutional Governance Kernel for AI Agents — trust scoring, approvals, audit trail

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package shows no immediate signs of malicious activity such as network calls or shell execution, but its metadata and newness raise concerns about potential supply-chain risks.

  • Metadata risk due to new repository and limited maintainer history
  • Low individual risk scores across other categories
Per-check LLM notes
  • Network: No network calls detected, which is normal unless the package requires external services.
  • Shell: No shell executions detected, indicating the package does not execute commands with elevated privileges.
  • Obfuscation: No obfuscation patterns detected, indicating low risk of malicious intent.
  • Credentials: No credential harvesting patterns detected, suggesting secure handling of sensitive information.
  • Metadata: The repository and package are newly created, with limited maintainer history, increasing suspicion.

🔬 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 created very recently: 7 day(s) ago (2026-05-30T13:47:35Z)

  • Repository created very recently: 7 day(s) ago (2026-05-30T13:47:35Z)
⚠ 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 agentguard-kernel 
Create a mini-application named 'TrustworthyBot' that leverages the 'agentguard-kernel' package to manage and govern interactions between users and AI agents. The application should provide a platform where users can submit tasks to AI agents, and these tasks are governed by a set of rules defined by the user. Here are the key functionalities and steps to develop this application:

1. **User Interface**: Design a simple web interface using Flask or Django where users can sign up/login, view available AI agents, and submit tasks.
2. **Task Submission**: Users should be able to submit tasks to AI agents along with specific guidelines/rules they want the AI agent to follow while executing the task.
3. **AgentGuard Integration**: Utilize the 'agentguard-kernel' package to assign a governance kernel to each AI agent. This kernel will enforce the rules provided by the user during task submission, ensuring the AI agent operates within the specified boundaries.
4. **Trust Scoring**: Implement a system to score the AI agent based on its adherence to the given rules and overall performance. This score should be visible to the user post-task completion.
5. **Audit Trail**: Maintain an audit log of all actions taken by the AI agents while performing tasks. This log should be accessible to the user for review purposes.
6. **Approval Mechanism**: Allow users to approve or reject the AI agent's actions based on their compliance with the rules. If an action is not compliant, the user should have the option to request the agent to redo the task.
7. **Reporting**: Develop a reporting feature that summarizes the performance of each AI agent over time, highlighting trends and areas for improvement.

The application should demonstrate the power of 'agentguard-kernel' in ensuring ethical and responsible use of AI by providing transparency, accountability, and control to users.