PromptShields

Secure AI Applications in 3 Lines of Code

An enterprise-grade, bidirectional LLM security framework. Defend against prompt injection, jailbreaks, data leakage, and PII exposure in production applications.

Installation

pip install promptshields

Optional extras

Core install covers pattern matching, session tracking, canary tokens, and the pre-trained ML ensemble. Some features need extra dependencies:

# Output DLP engine (Bloom filters, Aho-Corasick, semantic similarity)
pip install "promptshields[output]"

# Semantic/embedding-based matching (sentence-transformers)
pip install "promptshields[ml]"

# Framework integrations (LangChain, LiteLLM, LlamaIndex, CrewAI)
pip install "promptshields[integrations]"

# Everything
pip install "promptshields[all]"

Quick Start

from promptshield import Shield

shield = Shield.balanced()
result = shield.protect_input(user_input, system_prompt)

if result['blocked']:
    print(f"Blocked: {result['reason']} (score: {result['threat_level']:.2f})")
    print(f"Breakdown: {result['threat_breakdown']}")

Features & Capabilities

Protection Scope

• Prompt injection attacks (direct and indirect)
• Jailbreak attempts (DAN, persona replacement)
• System prompt extraction
• PII leakage and sensitive data exposure
• Session anomalies
• Encoded/obfuscated attacks (Base64, URL, Unicode)

Security Modes

Choose the right tier for your application latency requirements:

Shield.fast()       # ~1ms  - High throughput (pattern matching only)
Shield.balanced()   # ~2ms  - Production default (patterns + session tracking)
Shield.strict()     # ~7ms  - Sensitive apps (+ 1 ML model + PII detection)
Shield.secure()     # ~12ms - Maximum security (3 ML models ensemble)

Upgrading to v3.0.0

Version 3.0.0 introduces a massive update with the new bidirectional Output Filter.

Output Engine (Data Leakage Prevention)

Prevent sensitive data, PII, and proprietary knowledge from leaking through LLM generations securely before they reach the user.

• 4-Layer Scanning Pipeline: Defends against data leakage using Bloom Filters, Aho-Corasick exact matching, Honeypot traps, and Embedding-based Semantic Similarity checks.
• Semantic Leakage Detection: Natively utilizes sentence-transformers to detect when the LLM's output is highly semantically similar to your proprietary system prompts or private databases.
• Contextual PII Redaction: A heavily-optimized detection system to proactively redact sensitive information securely.

from promptshield import OutputFilter

filter = OutputFilter(
    system_prompt="You are a secret agent...",
    enforce_pii=True,
    enforce_embeddings=True
)

safe_text, was_redacted = filter.scan_output("My name is John Doe.")

Performance & Hardening

• Complete thread-safety for multi-tenant high-concurrency environments.
• Strict HMAC-SHA256 authenticated webhooks.
• Lazy-loading implementation for heavy dependencies (numpy, sentence-transformers) for lightning-fast cold starts.

Developer Experience

YAML Configuration

Launch shields declaratively without changing application code.

shield = Shield.from_config("promptshield.yml")

Slack and Teams Webhooks

Instantly trigger webhooks whenever high-severity threats are blocked natively.

shield = Shield.balanced(webhook_url="https://hooks.slack.com/...")

Async and FastAPI Support

Native middleware integration for modern web frameworks.

from promptshield import Shield
from promptshield.integrations.fastapi import PromptShieldMiddleware

app.add_middleware(PromptShieldMiddleware, shield=Shield.balanced())

Benchmark Results

Trained on the highly curated neuralchemy/Prompt-injection-dataset:

Pre-trained models available on Hugging Face:

• prompt-injection-detector
• prompt-injection-deberta

Documentation

Full API reference, guides, and integration details are available in the GitHub repository.

License

MIT License — see LICENSE

Built by Sanskar Jajoo / NeurAlchemy — AI Security and LLM Safety Research