UNPKG

@openguardrails/moltguard

Version:

AI agent security plugin for OpenClaw: prompt injection detection, PII sanitization, and monitoring dashboard

10 lines 437 B
/** * Local content sanitizer — strips PII and secrets before sending to API. * * Inspired by n8n's guardrails implementation (MIT). * Replaces sensitive data with category placeholders while preserving * the structure and context needed for injection detection. */ import type { SanitizeResult } from "./types.js"; export declare function sanitizeContent(content: string): SanitizeResult; //# sourceMappingURL=sanitizer.d.ts.map