Metadata-Version: 2.4
Name: interro-preventionai-scanner
Version: 0.1.0
Summary: Static analysis scanner for AI-agent production risks
Author: Interro
License-Expression: MIT
Project-URL: Homepage, https://github.com/interro/preventai
Keywords: ai,langgraph,safety,scanner,static-analysis
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Requires-Python: >=3.10
Description-Content-Type: text/markdown

# PreventAI Scanner

PreventAI Scanner is a Python static-analysis package for identifying production
risks in AI-agent systems. It currently checks source files for 23 risk patterns
related to tool replay, checkpoint isolation, retry storms, provider responses,
context growth, and related agent reliability failures.

## Install

```bash
python -m pip install interro-preventionai-scanner
```

## Scan a repository

```bash
prevention-scanner scan /path/to/repository
```

The scanner accepts Python, JavaScript, and TypeScript source files. Use JSON
output for CI integrations:

```bash
prevention-scanner scan /path/to/repository --format json
```

To run one or more rules:

```bash
prevention-scanner scan /path/to/repository --rule R-03 --rule R-11
```

## Development

```bash
python -m pip install -e .
python -m pytest -q
```

The current rules are heuristic static checks. Review findings before treating
them as release-blocking security or reliability decisions.
