azure-resource-graph

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, such as prompt injection, credential harvesting, or persistence mechanisms, were detected within the skill content.
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation from learn.microsoft.com and references tools from github.com/MicrosoftDocs/mcp. These are official, well-known, and trusted sources associated with the skill's author.
  • [DATA_EXFILTRATION]: Network operations are restricted to retrieving documentation from verified Microsoft endpoints. No unauthorized data access or exfiltration patterns were identified.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests external documentation, the data source is a well-known official service. The skill lacks capabilities for harmful command execution or file modification that would be exploitable via this vector.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:41 AM