Add prompt injection protection for AI endpoints

Implemented comprehensive security against prompt injection attacks:

**Detection Patterns:**
- System prompt manipulation (ignore/disregard/forget instructions)
- Role manipulation (pretend to be, act as)
- Data exfiltration (show system prompt, list users)
- Command injection (execute code, run command)
- Jailbreak attempts (DAN mode, developer mode, admin mode)

**Input Validation:**
- Maximum length: 2,000 characters
- Maximum line length: 500 characters
- Maximum repeated characters: 20 consecutive
- Special character ratio limit: 30%
- HTML/JavaScript injection blocking

**Sanitization:**
- HTML tag removal
- Zero-width character stripping
- Control character removal
- Whitespace normalization

**Rate Limiting:**
- 5 suspicious attempts per minute per user
- Automatic clearing on successful validation
- Per-user tracking with session storage

**Context Awareness:**
- Parenting keyword validation
- Domain-appropriate scope checking
- Lenient validation for short prompts

**Implementation:**
- lib/security/promptSecurity.ts - Core validation logic
- app/api/ai/chat/route.ts - Integrated validation
- scripts/test-prompt-injection.mjs - 19 test cases (all passing)
- lib/security/README.md - Documentation

**Test Coverage:**
✅ Valid parenting questions (2 tests)
✅ System manipulation attempts (4 tests)
✅ Role manipulation (1 test)
✅ Data exfiltration (3 tests)
✅ Command injection (2 tests)
✅ Jailbreak techniques (2 tests)
✅ Length attacks (2 tests)
✅ Character encoding attacks (2 tests)
✅ Edge cases (1 test)

All suspicious attempts are logged with user ID, reason, risk level,
and timestamp for security monitoring.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

maternal-web/app/api/ai/chat/route.ts

@@ -1,8 +1,9 @@
 import { NextRequest, NextResponse } from 'next/server';
 import { aiLimiter } from '@/lib/middleware/rateLimiter';
+import { validateAIPrompt, logSuspiciousPrompt } from '@/lib/security/promptSecurity';
 
 /**
- * AI chat endpoint with rate limiting
+ * AI chat endpoint with rate limiting and prompt injection protection
  * Limited to 10 queries per hour for free tier users
  */
 export async function POST(request: NextRequest) {
@@ -14,10 +15,46 @@ export async function POST(request: NextRequest) {
     const body = await request.json();
     const { message, childId, conversationId } = body;
 
+    // Validate message input
+    if (!message || typeof message !== 'string') {
+      return NextResponse.json(
+        {
+          error: 'AI_INVALID_INPUT',
+          message: 'Message must be a non-empty string',
+        },
+        { status: 400 }
+      );
+    }
+
+    // Validate and sanitize prompt for injection attempts
+    const validationResult = validateAIPrompt(message);
+
+    if (!validationResult.isValid) {
+      // Log security event
+      logSuspiciousPrompt(
+        message,
+        request.headers.get('x-user-id') || undefined,
+        validationResult.reason || 'Unknown',
+        validationResult.riskLevel
+      );
+
+      return NextResponse.json(
+        {
+          error: 'AI_PROMPT_REJECTED',
+          message: validationResult.reason || 'Your message could not be processed',
+          riskLevel: validationResult.riskLevel,
+        },
+        { status: 400 }
+      );
+    }
+
+    // Use sanitized prompt for AI request
+    const sanitizedMessage = validationResult.sanitizedPrompt || message;
+
     // TODO: Implement actual AI chat logic
     // This is a placeholder - actual AI integration will be handled by backend
 
-    // For now, forward to backend API
+    // For now, forward to backend API with sanitized message
     const backendUrl = process.env.NEXT_PUBLIC_API_URL || 'http://localhost:3020';
     const response = await fetch(`${backendUrl}/api/v1/ai/chat`, {
       method: 'POST',
@@ -26,7 +63,11 @@ export async function POST(request: NextRequest) {
         // Forward auth token from client
         Authorization: request.headers.get('Authorization') || '',
       },
-      body: JSON.stringify({ message, childId, conversationId }),
+      body: JSON.stringify({
+        message: sanitizedMessage, // Use sanitized message
+        childId,
+        conversationId,
+      }),
     });
 
     const data = await response.json();