Back to skill

Security audit

AANA Private Data Guardrail Skill

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only privacy guardrail that tells agents to minimize and redact sensitive data, with no code execution, persistence, or hidden data handling in the artifacts.

Reasonable to install as a privacy guardrail. If you configure an external checker, use only a trusted user- or administrator-approved service and send redacted summaries rather than raw secrets, full payment data, health records, legal records, or unrelated private messages.

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

Static analysis

No suspicious patterns detected.