Metadata-Version: 2.4
Name: razin
Version: 1.3.1
Summary: Static Analysis for LLM Agent Skills
Project-URL: Documentation, https://theinfosecguy.github.io/razin/
Project-URL: Repository, https://github.com/theinfosecguy/razin
Project-URL: Issues, https://github.com/theinfosecguy/razin/issues
Project-URL: Changelog, https://github.com/theinfosecguy/razin/releases
License-File: LICENSE
Requires-Python: >=3.12
Requires-Dist: pyyaml>=6.0.2
Description-Content-Type: text/markdown

<h1 align="center">Razin - Static analysis for LLM agent skills</h1>

<p align="center">
  <img src="https://github.com/user-attachments/assets/33c42667-0fff-4eac-a2d1-0f6d10441245" alt="razin" width="300" height="300" />
</p>

Razin is a local scanner for `SKILL.md`-defined agent skills.
It performs static analysis only (no execution) and writes deterministic findings.

## Documentation

Full documentation lives at:

- https://theinfosecguy.github.io/razin/

Canonical docs source in this repository:

- `docs/`

Use this README for quick start only.

## Requirements

- Python `3.12+`

## Install

```bash
pip install razin
razin --help
```

## Quick start

Run a scan:

```bash
razin scan -r . -o output/
```

Validate config:

```bash
razin validate-config -r .
```

### Common CI gates

```bash
# Fail if any high-severity finding exists
razin scan -r . --fail-on high --no-stdout

# Fail if aggregate score is 70 or above
razin scan -r . --fail-on-score 70 --no-stdout
```

### Output formats

```bash
# Default per-skill JSON reports
razin scan -r . -o output/ --output-format json

# Add CSV + SARIF exports
razin scan -r . -o output/ --output-format json,csv,sarif
```

## Local development

```bash
uv sync --dev
uv run pytest -q
uv run ruff check src tests
uv run mypy src tests
```

Docs preview and checks:

```bash
uv sync --group docs
uv run mkdocs serve
uv run mkdocs build --strict
uv run mdformat --check README.md docs
```

## Where to read more

- Getting started: `docs/getting-started.md`
- CLI reference: `docs/cli-reference.md`
- Configuration: `docs/configuration.md`
- Detectors: `docs/detectors.md`
- Output formats: `docs/output-formats.md`
- Docker workflow: `docs/docker.md`
- CI and exit codes: `docs/ci-and-exit-codes.md`
- Troubleshooting: `docs/troubleshooting.md`

## Contributing

See [CONTRIBUTING.md](CONTRIBUTING.md).

## Security

See [SECURITY.md](SECURITY.md).

## License

[MIT](LICENSE)
