skills/reason-machines/security-skills/enterprise-windows-infrastructure-security/Gen Agent Trust Hub
enterprise-windows-infrastructure-security
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions involve cloning a repository from a third-party GitHub organization that is not verified as a trusted source. Evidence:
git clone https://github.com/armourinfosec/Enterprise-Windows-Infrastructure-Security.gitinSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external markdown files from the cloned repository, creating a vulnerability surface where malicious instructions could be embedded in the ingested data. 1. Ingestion points: Markdown files and lab guides within the Enterprise-Windows-Infrastructure-Security repository folder. 2. Boundary markers: Absent; the instructions do not include delimiters or specific guidance for the agent to disregard instructions within the external vault files. 3. Capability inventory: The skill provides extensive PowerShell administrative capabilities across multiple sections of SKILL.md, including New-ADUser, Set-GPRegistryValue, Install-WindowsFeature, and Set-NetFirewallProfile. 4. Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill contains a large library of PowerShell command snippets for sensitive administrative and security operations on Windows Server environments. Evidence: Multiple code blocks in SKILL.md provide templates for domain management, infrastructure configuration, and system hardening.
Audit Metadata