azure-resource-manager

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill functions as a documentation lookup tool.
  • [EXTERNAL_DOWNLOADS]: All external URLs point to learn.microsoft.com, which is an official and trusted Microsoft domain. This aligns with the skill's purpose and follows the trusted vendor rules.
  • [PROMPT_INJECTION]: The instructions provided for the agent are standard operational guidelines for navigating the documentation index and do not attempt to bypass safety filters or override system behavior.
  • [DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were identified. The network access is scoped to fetching documentation from trusted sources using established MCP tools.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 09:41 AM
Security Audit — agent-trust-hub — azure-resource-manager