openrouter-data-privacy

# OpenRouter Data Privacy ## Overview When sending data through OpenRouter to upstream LLM providers, you're responsible for ensuring prompts don't leak PII inappropriately. OpenRouter itself does not train on API data, but each upstream provider has its own data retention and training policies. This skill covers PII detection and redaction, placeholder substitution, provider selection for privacy, and consent tracking. ## PII Detection and Redaction ```python import re from dataclasses import dataclass from typing import Optional @dataclass class PiiScanResult: clean_text: str findings: list[dict] has_pii: bool PII_RULES = [ ("email", r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'), ("phone", r'\b(?:\+1[-.\s]?)?\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}\b'), ("ssn", r'\b\d{3}-\d{2}-\d{4}\b'), ("credit_card", r'\b(?:\d{4}[- ]?){3}\d{4}\b'), ("api_key", r'\bsk-or-v1-[a-zA-Z0-9]+\b'), ("ip_address", r'\b(?:\d{1,3}\.){3}\d{1,3}\b'), ] REPLACEMENTS = { "email": "[EMAIL]", "phone": "[PHONE]", "ssn": "[SSN]", "credit_card": "[CARD]", "api_key": "[API_KEY]", "ip_address": "[IP]", } def scan_and_redact(text: str) -> PiiScanResult: """Scan text for PII and return redacted version with findings.""" findings = [] clean = text for pii_type, pattern in PII_RULES: matches = re.findall(pattern, clean) for match in matches: findings.append({"type": pii_type, "value_prefix": match[:4] + "..."}) ...