Metadata-Version: 2.4
Name: brack
Version: 0.5.0
Summary: Runtime security oracle for AI agents. Scan prompts, tool calls, and outputs before execution.
Home-page: https://github.com/brack-6/brack
Author: brack-6
Keywords: ai agent security prompt-injection llm runtime oracle x402
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Topic :: Security
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: requires-python
Dynamic: summary

# brack

Runtime security oracle for AI agents.

```bash
pip install brack
```

```python
from brack import BrackClient

brack = BrackClient()  # free tier, 200 calls

result = brack.scan("user input here")
# {"verdict": "ALLOW", "confidence": 0.15, ...}

if brack.prompt_risk(user_input)["risk"] == "high":
    raise BlockedInput("injection detected")
```

Full docs: https://github.com/brack-6/brack
