Back to skill

Security audit

Windows Multi-Tool Suite

Security checks for vulnerabilities and agentic risk

Overview

The scripts fit the suite’s purpose, but misleading assurances about Windows security and broad script-unblocking advice warrant review.

Verify each script before unblocking it, preserve Defender and workplace security policies, and review the three separately installed skills. The optional unsigned desktop app is outside this inspection; a matching publisher-supplied hash does not establish safety.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The FAQ instructs users to unblock downloaded scripts without warning that this removes a Windows security marker.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The FAQ recommends unblocking an entire scripts folder without explaining that Unblock-File removes the Mark-of-the-Web security marker and can eliminate origin-based PowerShell execution restrictions. This is more concerning in a setup intended for work machines because the statement that Defender has nothing to block is misleading: scripts can contain malicious code, and an altered download could execute with the user's access after unblocking. No malicious payload is demonstrated here, but the guidance weakens a security boundary without adequate qualification.

Content

No source excerpt is available for this finding.

The user-profile-only guarantee is not enforced for a custom workspace.

Low
Category
Excessive Agency
Confidence
96% confidence
Finding

The header at L003-L005 explicitly promises that setup does not touch anything outside the user's profile. However, a supplied -Workspace value is used without confinement checks to create directories and copy configuration files at L092-L103, allowing writes to any destination accessible to the current user, including locations outside that profile.

Content

No source excerpt is available for this finding.