🤖 AI Analysis

Final verdict: SUSPICIOUS

The package has moderate shell risk due to subprocess execution and low metadata quality, raising concerns about its maintenance and authenticity.

Moderate shell risk due to subprocess execution
Low metadata quality and maintainer activity

Per-check LLM notes

Network: No network calls detected, indicating low risk of data exfiltration.
Shell: Subprocess execution is observed but without clear malicious intent from the provided context, suggesting moderate risk.
Obfuscation: No obfuscation patterns detected, indicating low risk.
Credentials: No credential harvesting patterns detected, indicating low risk.
Metadata: The package shows several red flags indicating low maintainer activity and poor metadata quality, which may suggest potential risk.

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 8.0

Found 4 shell execution pattern(s)

date(env_override) return subprocess.run( [sys.executable, "-m", "agentmeter.hook"],
th) -> None: result = subprocess.run( [sys.executable, "-m", "agentmeter.hook"],
date(env_override) return subprocess.run( [sys.executable, "-m", module], input=json.
th) -> None: result = subprocess.run( [sys.executable, "-m", self.MODULE],

✓ 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

No GitHub repository linked

No GitHub repository link found

⚠ Maintainer History score 8.0

4 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)
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-usage

Develop a Python-based mini-application named 'CostGuard' that leverages the 'agent-usage' package to monitor and manage costs associated with AI coding agents. The application should serve as a cost intelligence tool for developers who use various AI coding assistants, providing insights into the financial implications of their usage patterns.

Step-by-step requirements:
1. **Setup and Configuration**: The application should allow users to configure it with API keys from different AI coding agents they use. This includes setting up authentication for services like GitHub Copilot, Codegen, etc., through environment variables or a configuration file.
2. **Agent Usage Tracking**: Integrate the 'agent-usage' package to track the usage of these agents in real-time. The application should log every instance of agent usage, including the type of service, duration, and any specific parameters that affect cost.
3. **Cost Estimation**: Utilize the 'agent-usage' package's capabilities to estimate costs based on historical data and current usage trends. The application should provide both daily and monthly cost projections.
4. **Budget Alerts**: Implement a feature where users can set budget thresholds. If the estimated cost exceeds a predefined threshold, the application should send notifications via email or SMS.
5. **Usage Reports**: Provide comprehensive reports summarizing the usage and costs over different periods. Users should be able to filter reports by date range, agent type, or specific projects.
6. **Integration with External Tools**: Consider integrating 'CostGuard' with popular project management tools such as Jira or Trello to enhance its utility for teams.
7. **User Interface**: Develop a simple web interface using Flask or Django for users to interact with 'CostGuard'. This UI should allow easy access to all functionalities including setting budgets, viewing reports, and configuring agents.

Suggested Features:
- Real-time cost monitoring dashboard
- Historical trend analysis
- Customizable alerts with multiple notification channels
- Support for multiple user accounts within a single organization

The 'agent-usage' package will be used extensively for its ability to monitor and analyze the cost implications of AI coding agent usage. By leveraging this package, 'CostGuard' aims to help developers make informed decisions about their AI tool investments, ensuring efficient resource utilization without compromising productivity.