azure-iot-operations
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of documentation pointers and operational instructions for the AI agent. No malicious code, credential theft, or unauthorized data access patterns were detected.
- [EXTERNAL_DOWNLOADS]: The skill utilizes tools to retrieve documentation from 'learn.microsoft.com' and suggests installing a Model Context Protocol (MCP) server from 'github.com/MicrosoftDocs'. These are well-known, trusted domains owned by the authoring organization.
- [PROMPT_INJECTION]: Instructions marked as 'IMPORTANT for Agent' provide benign guidance on tool usage and file reading optimization. They do not attempt to bypass safety filters or override the agent's core instructions.
- [COMMAND_EXECUTION]: While the skill mentions deploying services via Azure CLI or Kubernetes, it does so in the context of documentation and does not contain any automated or hidden command execution scripts.
Audit Metadata