Skills
Navigate
skills/microsoftdocs/agent-skills/azure-managed-grafana/Gen Agent Trust Hub

azure-managed-grafana

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches Markdown documentation from learn.microsoft.com using the mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage tools. These requests are directed to a well-known service and include identifying query parameters for telemetry.
  • [INDIRECT_PROMPT_INJECTION]: The skill serves as a surface for indirect prompt injection because it ingests untrusted data from the web (documentation content). However, the ingestion points are restricted to official Microsoft domains. The skill does not currently implement specific boundary markers for the fetched content, but this is a standard risk for documentation-fetching skills.
  • [COMMAND_EXECUTION]: The instructions recommend that the user install the mcp_microsoftdocs tool via an official GitHub repository (MicrosoftDocs/mcp) if it is not present. This is a transparent recommendation for standard setup and does not involve automated or suspicious execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 07:03 AM