Metadata-Version: 2.4
Name: promptshield-firewall
Version: 0.1.1
Summary: Real-time LLM prompt injection firewall
Home-page: https://promptshield.live
Author: Kehinde Omosor
Author-email: kehinde@promptshield.live
Keywords: llm security prompt injection firewall ai
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Security
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: httpx>=0.24.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# PromptShield Python SDK

Real-time LLM prompt injection firewall.

## Installation

```bash
pip install promptshield
```

## Quick Start

```python
from promptshield import PromptShield

shield = PromptShield(api_key="ps_your_key")

# Scan before sending to your LLM
result = shield.scan("Ignore all previous instructions.")

if result["verdict"] == "BLOCKED":
    print(f"Attack blocked! Risk score: {result['risk_score']}")
else:
    response = your_llm.chat(user_input)

# Or use the simple boolean check
if not shield.is_safe(user_input):
    return "Request blocked."
```

## Async Support

```python
result = await shield.async_scan(user_input)
```

## Get API Key

Free tier at [promptshield.live](https://promptshield.live)
