Houtini-lm

Instructions

Implementation Reference

• src/prompts/analyze/security-audit.ts:123-146 (handler)

  The main execute method of the SecurityAuditor class, which implements the core logic for the 'security_audit' tool. It detects single-file or multi-file mode, validates params, sets up the model, and routes to the appropriate analysis handler.
  async execute(params: any, llmClient: any) { return await withSecurity(this, params, llmClient, async (secureParams) => { try { // 1. Auto-detect analysis mode based on parameters const analysisMode = this.detectAnalysisMode(secureParams); // 2. Validate parameters based on detected mode this.validateParameters(secureParams, analysisMode); // 3. Setup model const { model, contextLength } = await ModelSetup.getReadyModel(llmClient); // 4. Route to appropriate analysis method if (analysisMode === 'single-file') { return await this.executeSingleFileAnalysis(secureParams, model, contextLength); } else { return await this.executeMultiFileAnalysis(secureParams, model, contextLength); } } catch (error: any) { return ErrorHandler.createExecutionError('security_audit', error); } }); }
• src/prompts/analyze/security-audit.ts:27-113 (schema)

  Tool metadata including name 'security_audit' and complete input parameters schema supporting single-file and multi-file security audits.
  name = 'security_audit'; category = 'analyze' as const; description = 'Perform comprehensive security audit across entire project, analyzing data flows, authentication chains, and cross-file vulnerabilities with OWASP compliance checking'; // Universal parameter set - supports both single and multi-file scenarios parameters = { // Single-file parameters code: { type: 'string' as const, description: 'The code to analyze for security issues (for single-file analysis)', required: false }, filePath: { type: 'string' as const, description: 'Path to single file to analyze for security vulnerabilities', required: false }, // Multi-file parameters projectPath: { type: 'string' as const, description: 'Absolute path to project root directory', required: false }, files: { type: 'array' as const, description: 'Array of specific file paths (for multi-file analysis)', required: false, items: { type: 'string' as const } }, maxDepth: { type: 'number' as const, description: 'Maximum directory depth for multi-file discovery (1-5)', required: false, default: 4 }, // Security-specific parameters projectType: { type: 'string' as const, description: 'Project type for specific security checks', required: false, enum: ['wordpress-plugin', 'wordpress-theme', 'react-app', 'react-component', 'node-api', 'browser-extension', 'cli-tool', 'n8n-node', 'n8n-workflow', 'html-component', 'generic'], default: 'generic' }, auditDepth: { type: 'string' as const, description: 'Depth of security audit', enum: ['basic', 'standard', 'comprehensive'], default: 'standard', required: false }, includeOwasp: { type: 'boolean' as const, description: 'Include OWASP Top 10 checks', required: false, default: true }, focusAreas: { type: 'array' as const, description: 'Specific areas to focus on: authentication, data-flow, input-validation, authorization', required: false, items: { type: 'string' as const } }, // Universal parameters language: { type: 'string' as const, description: 'Programming language', required: false, default: 'javascript' }, analysisDepth: { type: 'string' as const, description: 'Level of analysis detail', enum: ['basic', 'detailed', 'comprehensive'], default: 'detailed', required: false }, analysisType: { type: 'string' as const, description: 'Type of analysis to perform', enum: ['security', 'owasp', 'comprehensive'], default: 'comprehensive', required: false } };
• src/validation/schemas.ts:34-69 (schema)

  Output schema definition for security_audit responses, defining structure for summary, vulnerabilities, dependencies, etc.
  export interface SecurityAuditResponse extends BaseResponse { data: { summary: { riskLevel: "critical" | "high" | "medium" | "low"; totalVulnerabilities: number; criticalCount: number; highCount: number; mediumCount: number; lowCount: number; }; vulnerabilities: Array<{ type: string; severity: "critical" | "high" | "medium" | "low"; description: string; location: { file?: string; line?: number; column?: number; code?: string; }; recommendation: string; owaspCategory?: string; cwe?: string; }>; dependencies?: { vulnerable: Array<{ packageName: string; version: string; vulnerability: string; severity: string; }>; }; recommendations: string[]; passedChecks: string[]; }; }
• src/validation/schemas.ts:520-520 (registration)

  Registration of 'security_audit' tool in the FunctionResponseMap type mapping.
  'security_audit': SecurityAuditResponse;
• src/validation/response-factory.ts:65-86 (helper)

  Helper factory method to create properly formatted SecurityAuditResponse objects.
  static createSecurityAuditResponse( summary: SecurityAuditResponse['data']['summary'], vulnerabilities: SecurityAuditResponse['data']['vulnerabilities'], recommendations: string[], passedChecks: string[], dependencies: SecurityAuditResponse['data']['dependencies'] | undefined, modelUsed: string ): SecurityAuditResponse { return { success: true, timestamp: new Date().toISOString(), modelUsed, executionTimeMs: this.getExecutionTime(), data: { summary, vulnerabilities, dependencies, recommendations, passedChecks } }; }