Back to skill

Security audit

Memory Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed memory-maintenance workflow skill with no bundled executable code, though its referenced PowerShell scripts are missing and should be verified before use.

Installers should treat this as a workflow guide rather than a complete tool package unless the missing scripts are supplied separately. Before running any referenced pwsh command, confirm the script path points to the intended trusted script and review it, especially for repair or archive operations that may modify memory 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

Static analysis

No suspicious patterns detected.