Trust Assessment
ms365-tenant-manager received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 25 findings: 1 critical, 24 high, 0 medium, and 0 low severity. Key findings include Hidden network beacons / undisclosed telemetry, PowerShell Command Injection via Unsanitized Input in Generated Scripts.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings25
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | PowerShell Command Injection via Unsanitized Input in Generated Scripts The Python scripts `scripts/powershell_generator.py` and `scripts/user_management.py` are designed to generate PowerShell scripts for Microsoft 365 administration. These Python scripts construct PowerShell commands by directly interpolating input values (e.g., policy names, user principal names, display names, department names) into double-quoted strings within the generated PowerShell code. This process lacks proper sanitization or escaping of special characters. If an attacker can control these input values (e.g., through a crafted CSV file or API call parameters), they can inject arbitrary PowerShell commands by including malicious syntax (e.g., `"; <malicious_command>; #"`) that breaks out of the string literal. When the generated PowerShell script is subsequently executed by a user (likely a Global Administrator), these injected commands would run with elevated privileges, leading to arbitrary code execution and potential tenant compromise. Implement robust input sanitization and escaping for all user-controlled or configuration-derived strings before interpolating them into the generated PowerShell scripts. For PowerShell, this typically involves escaping double quotes (`"` to `""`), backticks, and other special characters, or using safe string formatting methods. A more secure approach would be to pass parameters to the generated PowerShell scripts in a structured way (e.g., as script parameters) rather than embedding them directly into string literals, allowing PowerShell's parser to handle the values safely. | LLM | scripts/powershell_generator.py, scripts/user_management.py:55 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:90 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:91 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:157 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:181 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:204 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:213 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:232 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:254 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:265 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:272 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:273 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:274 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:275 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:278 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:279 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:283 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:357 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:421 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/powershell_generator.py:423 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/user_management.py:87 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/user_management.py:116 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/user_management.py:175 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/user_management.py:190 | |
| HIGH | Hidden network beacons / undisclosed telemetry DNS query with variable subdomain (DNS exfiltration) Remove undisclosed network calls and telemetry. All outbound communication should be documented and necessary for the skill's stated purpose. BCC injection in email tools is almost always malicious. | Manifest | skills/alirezarezvani/ms365-tenant-manager/scripts/user_management.py:199 |
Scan History
Embed Code
[](https://skillshield.io/report/bdcc92f08d5fd69a)
Powered by SkillShield