Back to skill

Security audit

powershell

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives narrow guidance to avoid PowerShell text-writing methods that can corrupt UTF-8 content on Windows.

This appears safe to install if you want agents on Windows to avoid PowerShell file writes that may corrupt UTF-8 text. Be aware it is workflow guidance, so it may steer the agent toward dedicated file-editing tools or explicit UTF-8 writes when editing files.

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