azure-compliance

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data from Azure compliance scans and Resource Graph queries, creating a surface for indirect prompt injection.
  • Ingestion points: Analysis of Excel reports (Recommendations and ImpactedResources sheets) and Resource Graph query results as described in references/azure-quick-review.md and references/azure-resource-graph.md.
  • Boundary markers: Absent; the skill does not provide instructions to the agent to treat data from Azure scans as untrusted or to ignore embedded instructions within resource properties.
  • Capability inventory: The skill has access to powerful Azure management capabilities via the mcp_azure_mcp_extension_azqr and mcp_azure_mcp_extension_cli_generate MCP tools.
  • Sanitization: Absent; there are no explicit validation or escaping mechanisms for the resource metadata processed by the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 05:58 PM