azure-custom-vision

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from learn.microsoft.com using the mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage tools. These are well-known, official services used to provide up-to-date documentation to the agent.
  • [EXTERNAL_DOWNLOADS]: It provides a reference link to the MicrosoftDocs/mcp repository on GitHub for tool installation instructions. This targets an official repository of a trusted organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves external content from the web to fulfill its purpose. This creates a surface for indirect prompt injection where instructions in the fetched documentation could influence the agent. However, the data sources are restricted to official Microsoft documentation domains, which are considered highly trusted and reputable.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:20 PM