aks-cluster-setup

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill processes user-supplied requirements to generate infrastructure configurations and CLI commands. • Ingestion points: User-defined parameters for cluster scale, region, and networking in SKILL.md. • Boundary markers: The skill does not currently implement specific boundary markers to isolate user input from its internal logic. • Capability inventory: The skill generates and references az aks commands and MCP tool calls for cluster management. • Sanitization: There is no explicit validation or sanitization defined for the architectural inputs provided by the user.
  • Command Execution: The skill includes a reference for common Azure CLI operations. • Evidence: references/cli-reference.md contains commands for cluster creation, management, and monitoring. • This functionality allows the agent to translate user intent into actionable cloud operations within the Azure ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 08:18 AM
Security Audit — agent-trust-hub — aks-cluster-setup