ms365-tenant-manager

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill uses Python modules (user_management.py, powershell_generator.py, and tenant_setup.py) to dynamically generate PowerShell scripts through string interpolation and f-strings. This is the primary function of the skill, facilitating the creation of administrative scripts from user configuration and CSV data.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect injection as it processes untrusted data (CSV inputs) and interpolates it into high-privilege scripts.
  • Ingestion points: Untrusted data enters the context via CSV file paths and dictionaries in user_management.py and powershell_generator.py.
  • Boundary markers: The generated PowerShell scripts do not implement specific delimiters or 'ignore' instructions to encapsulate interpolated user data.
  • Capability inventory: The skill generates scripts capable of high-privilege operations, including modifying Conditional Access policies (New-MgIdentityConditionalAccessPolicy), converting mailboxes (Set-Mailbox), and managing licenses (Set-MgUserLicense).
  • Sanitization: The code performs no explicit escaping or validation of special characters (e.g., quotes or semicolons) within user-provided strings before they are embedded into the PowerShell command structure.
  • [EXTERNAL_DOWNLOADS]: The skill's documentation correctly references the installation of official, well-known PowerShell modules from Microsoft (Microsoft.Graph, ExchangeOnlineManagement, and MicrosoftTeams) required for its operation. These references are documented neutrally as standard prerequisites for M365 administration.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 03:14 PM