ms365-tenant-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODEEXTERNAL_DOWNLOADS
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect prompt injection surface identified.
  • Ingestion points: CSV and JSON files for user management as described in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: High-privilege PowerShell script generation via powershell_generator.py.
  • Sanitization: Absent.
  • COMMAND_EXECUTION (LOW): The skill generates PowerShell scripts for administrative actions. This dynamic code generation is standard for the tool's purpose but represents a potential risk if inputs are not sanitized.
  • NO_CODE (SAFE): Several Python implementation scripts (e.g., powershell_generator.py, tenant_setup.py) were not provided in the skill files for review.
  • EXTERNAL_DOWNLOADS (LOW): The skill requires standard PowerShell modules (e.g., Microsoft.Graph) from the PowerShell Gallery.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM