cli-microsoft365-script

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates processing untrusted data from external files and using it within administrative commands.
  • Ingestion points: Data is ingested from external CSV files using Import-Csv in SKILL.md.
  • Boundary markers: Absent; data fields from external files are directly interpolated into command arguments without delimiters or 'ignore' instructions.
  • Capability inventory: The skill leverages the m365 CLI, which has extensive capabilities for modifying Microsoft 365 tenant configurations, including Entra ID user management and SharePoint site operations.
  • Sanitization: Absent; the provided templates do not include validation or sanitization logic for data retrieved from external sources before it is passed to CLI commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 11:07 AM