guardrails-safety-filter-builder

Guardrails & Safety Filter Builder

Build comprehensive safety systems for LLM applications.

Safety Layers

1. Input filtering: Block malicious prompts
2. Output filtering: Redact sensitive data
3. Topic constraints: Policy-based refusals
4. PII detection: Mask personal information
5. Prompt injection: Detect manipulation attempts

PII Detection & Redaction

import re
from presidio_analyzer import AnalyzerEngine
from presidio_anonymizer import AnonymizerEngine

analyzer = AnalyzerEngine()
anonymizer = AnonymizerEngine()

def redact_pii(text: str) -> str:
    # Detect PII
    results = analyzer.analyze(
        text=text,
        language='en',
        entities=["EMAIL_ADDRESS", "PHONE_NUMBER", "CREDIT_CARD", "SSN"]
    )

    # Anonymize
    anonymized = anonymizer.anonymize(text, results)
    return anonymized.text

# Example: "My email is [email protected]" → "My email is <EMAIL_ADDRESS>"

Prompt Injection Detection

def detect_prompt_injection(user_input: str) -> bool:
    """Detect common prompt injection patterns"""
    patterns = [
        r'ignore (previous|above) instructions',
        r'disregard (all|any) (prior|previous)',
        r'you are now',
        r'new instructions',
        r'system:',
        r'override',
    ]

    for pattern in patterns:
        if re.search(pattern, user_input, re.IGNORECASE):
            return True

    return False

# Block if detected
if detect_prompt_injection(user_input):
    return "I cannot process that request."

Topic Constraints

# Define allowed/disallowed topics
POLICY = {
    "allowed_topics": [
        "product_features",
        "troubleshooting",
        "billing",
        "account_management"
    ],
    "disallowed_topics": [
        "medical_advice",
        "legal_advice",
        "financial_advice",
        "politics",
        "violence"
    ],
    "requires_disclaimer": [
        "security_practices",
        "data_privacy"
    ]
}

# Classify topic
def classify_topic(query: str) -> str:
    classification_prompt = f"""
    Classify this query into one of these topics:
    {', '.join(POLICY['allowed_topics'] + POLICY['disallowed_topics'])}

    Query: {query}

    Return only the topic name.
    """
    return llm(classification_prompt)

# Check policy
def check_policy(query: str) -> dict:
    topic = classify_topic(query)

    if topic in POLICY["disallowed_topics"]:
        return {
            "allowed": False,
            "reason": f"Cannot provide {topic}",
            "refusal": REFUSAL_TEMPLATES[topic]
        }

    return {"allowed": True, "topic": topic}