feat: implement prompt injection protection and OpenRouter paid API key support
- Add comprehensive prompt injection security module with 160+ attack pattern detection - Implement security checks in message handling with proper blocking and user feedback - Add OpenRouter paid API key support (OPENROUTER_PAID_API_KEY) for premium models - Update model discovery and chat functions to use paid API key for premium models - Add comprehensive test suite with 434 test cases (98.39% accuracy) - Tests cover legitimate WordPress development queries, injection attacks, obfuscated attempts - Improve builder loading indicators with text-based progress (building/planning) - Replace spinning animations with 'Starting build/planning process' messages
This commit is contained in:
19
chat/security/index.js
Normal file
19
chat/security/index.js
Normal file
@@ -0,0 +1,19 @@
|
||||
/**
|
||||
* Security Module Index
|
||||
*
|
||||
* Centralized exports for all security-related functionality.
|
||||
* Import this module to access all security validators and sanitizers.
|
||||
*/
|
||||
|
||||
const promptSanitizer = require('./prompt-sanitizer');
|
||||
|
||||
module.exports = {
|
||||
// Prompt injection detection
|
||||
sanitizeUserInput: promptSanitizer.sanitizeUserInput,
|
||||
shouldBlockInput: promptSanitizer.shouldBlockInput,
|
||||
wrapUserContent: promptSanitizer.wrapUserContent,
|
||||
createHardenedSystemPrompt: promptSanitizer.createHardenedSystemPrompt,
|
||||
|
||||
// Re-export full module for advanced use
|
||||
promptSanitizer,
|
||||
};
|
||||
Reference in New Issue
Block a user