mistral-security-basics

# Mistral Security Basics ## Overview Security practices for Mistral AI integrations: API key management, prompt injection defense, output sanitization, content moderation with `mistral-moderation-latest`, request logging without secrets, and key rotation. ## Prerequisites - Mistral API key provisioned - Understanding of OWASP LLM Top 10 risks - Secret management infrastructure ## Instructions ### Step 1: API Key Management ```python import os # NEVER: api_key = "sk-abc123" # Development — env vars api_key = os.environ.get("MISTRAL_API_KEY") if not api_key: raise RuntimeError("MISTRAL_API_KEY not set") # Production — secret manager from google.cloud import secretmanager def get_api_key() -> str: client = secretmanager.SecretManagerServiceClient() response = client.access_secret_version( name="projects/my-project/secrets/mistral-api-key/versions/latest" ) return response.payload.data.decode("UTF-8") ``` ### Step 2: Prompt Injection Defense ```typescript function sanitizeUserInput(input: string): string { // Strip common injection patterns const patterns = [ /ignore (?:previous|all|above) instructions/gi, /you are now/gi, /system prompt/gi, /\boverride\b/gi, /\bforget\b.*\binstructions\b/gi, ]; let sanitized = input; for (const pattern of patterns) { sanitized = sanitized.replace(pattern, '[FILTERED]'); } // Limit length to prevent context stuffing return sanitized.slice(0, 4000); } function build...