azure-iot-operations

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation from learn.microsoft.com. This is a well-known and trusted service, and these references represent normal documentation functionality.
  • [REMOTE_CODE_EXECUTION]: Instructions are provided to install the mcp_microsoftdocs tool from the official MicrosoftDocs GitHub repository. This represents a reference to a trusted organization's official tooling rather than a security risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill features an attack surface for indirect prompt injection by fetching content from external URLs.
  • Ingestion points: External technical documentation retrieved from learn.microsoft.com.
  • Boundary markers: Relies on the agent's default handling of tool outputs from fetch_webpage and microsoft_docs_fetch.
  • Capability inventory: The skill utilizes local file reading and specific MCP tool invocations for documentation retrieval.
  • Sanitization: Content is sourced exclusively from official, trusted Microsoft documentation domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 12:23 AM