ClawHub
Back to skill

Security audit

Windows

Security checks for vulnerabilities and agentic risk

Overview

This is a Windows operations reference skill with no executable payload, but users should treat its WinRM and system-configuration tips carefully.

Install only if you want Windows administration guidance. Before applying its examples, use placeholders instead of real secrets, keep Defender exclusions narrow, avoid broad TrustedHosts entries, and prefer HTTPS or Kerberos-protected remoting for administrative sessions.

A.I.G

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

SkillSpector

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
Findings (3)

Instruction Override

High
Category
Prompt Injection
Confidence
70% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 34)May include surrounding context.

md
## Symbolic Links

- Creating symlinks requires admin OR SeCreateSymbolicLinkPrivilege — regular users fail silently
- Enable Developer Mode for symlinks without admin: Settings → For Developers → Developer Mode
- `mklink` is CMD-only, PowerShell uses `New-Item -ItemType SymbolicLink`

## Script Signing

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advises configuring WinRM TrustedHosts on workgroup machines but omits that TrustedHosts weakens server identity validation and can enable connections to spoofed or unintended hosts. In a security/automation skill, presenting this as routine setup without scoping, minimization, or compensating controls can lead users to adopt insecure remoting practices.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill states that HTTP WinRM sends credentials readable on the network, but it stops short of clearly prohibiting or strongly discouraging insecure HTTP remoting. Because this is operational guidance, readers may still treat HTTP as acceptable, exposing credentials and session contents to interception or relay on untrusted networks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.