Back to skill

Security audit

AANA Private Data Guardrail Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent instruction-only privacy guardrail that tells agents to minimize and redact private data rather than collect, execute, persist, or disclose it automatically.

Install this as a privacy review aid, not as a compliance system. If connecting it to an external checker, ensure that checker is trusted and configured to receive only redacted summaries, not raw secrets, full payment data, health records, legal records, or private messages.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep