Trust Assessment
windows-builder received a trust score of 48/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 1 critical, 1 high, 1 medium, and 0 low severity. Key findings include Insecure WinRM Configuration Exposes Credentials, Unverified Remote Script Execution (Chocolatey Installation), PowerShell Execution Policy Bypass.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, static_code_analysis, dependency_graph. The static_code_analysis layer scored lowest at 48/100, indicating areas for improvement.
Last analyzed on February 11, 2026 (commit 98272896). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Insecure WinRM Configuration Exposes Credentials The provided WinRM setup script and Packer configurations explicitly allow unencrypted WinRM communication (`AllowUnencrypted="true"`, `Basic="true"`) and disable SSL certificate validation (`winrm_insecure = true`). This makes credentials (e.g., 'Administrator' password) and other sensitive data transmitted over WinRM vulnerable to eavesdropping and Man-in-the-Middle (MITM) attacks. This is present in both AWS and Azure examples, and the `setup-winrm.ps1` script. Enable SSL with proper certificate validation (`winrm_insecure = false`), ensure `AllowUnencrypted` is `false`, and use more secure authentication methods than Basic over unencrypted channels. Ensure WinRM traffic is encrypted and authenticated to protect sensitive data. | Unknown | SKILL.md:30 | |
| HIGH | Unverified Remote Script Execution (Chocolatey Installation) The skill uses `iex ((New-Object System.Net.WebClient).DownloadString('https://community.chocolatey.org/install.ps1'))` to install Chocolatey. This downloads and executes a script directly from an external URL without any integrity checks (e.g., hash verification) or pinning to a specific version. This introduces a significant supply chain risk, as a compromise of the external server or the script itself could lead to arbitrary code execution on the build machine. Avoid direct execution of unverified remote scripts. Download the script, verify its integrity (e.g., against a known hash), and then execute it locally. Alternatively, use a trusted package manager or pre-baked images with Chocolatey already installed, or host the installation script in a controlled environment. | Unknown | SKILL.md:99 | |
| MEDIUM | PowerShell Execution Policy Bypass The skill explicitly sets the PowerShell execution policy to `Bypass` for the current process (`Set-ExecutionPolicy Bypass -Scope Process -Force`). While common for automated scripts, this reduces the security posture of the system by allowing unsigned and potentially malicious scripts to execute without warning. This could facilitate further attacks if other vulnerabilities are present or if a compromised script is introduced. Use a more restrictive execution policy (e.g., `RemoteSigned`) and sign scripts, or ensure that scripts are executed in a highly controlled and isolated environment. Evaluate if `Bypass` is strictly necessary or if a more secure alternative can be used, such as executing specific scripts with `powershell.exe -ExecutionPolicy Bypass -File script.ps1` rather than setting it globally for the process. | Unknown | SKILL.md:97 |
Scan History
Embed Code
[](https://skillshield.io/report/7ea47f8495f05e33)
Powered by SkillShield