ninjaone-specialist
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides templates and instructions for executing PowerShell commands with elevated privileges (
#Requires -RunAsAdministrator). This is standard functionality for RMM (Remote Monitoring and Management) tasks such as system diagnostics and maintenance. - [EXTERNAL_DOWNLOADS]: The documentation references external resources including the official NinjaOne GitHub, a community repository (
fyxtro/NinjaRMM-Scripts), and a technical blog (homotechsual.dev) for technical reference and script examples. - [PROMPT_INJECTION]: The skill describes an attack surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via NinjaOne environment variables (
$env:) and Custom Fields (Ninja-Property-Get) as documented inSKILL.md. - Boundary markers: Absent. The templates do not use delimiters or warnings to ignore instructions embedded in the retrieved system data.
- Capability inventory: The skill facilitates local file writing (
Add-ContenttoC:\Windows\Temp\), script execution with administrator privileges, and writing data back to the RMM platform (Ninja-Property-Set). - Sanitization: Absent. The provided templates do not implement escaping or validation of the data retrieved from the environment before it is used in logic or reports.
Audit Metadata