azure-ai-vision

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to fetch documentation from learn.microsoft.com. This is an official, well-known, and trusted domain for Microsoft technical documentation.
  • [PROMPT_INJECTION]: Contains instructions labeled 'IMPORTANT for Agent'. These are standard operational guidelines to help the agent manage large file reads and tool usage, and do not attempt to bypass safety filters or override core instructions.
  • [DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were detected. Network operations are limited to retrieving documentation from trusted sources.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unauthorized package installations were found. The skill suggests the use of the mcp_microsoftdocs tool, which is a recognized extension for accessing documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:41 AM