azure-aks
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes high-privilege administrative tasks on Azure Kubernetes clusters through 'az' and 'kubectl', including operations such as cluster upgrades, node pool scaling, and stopping services.
- [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection via command parameter interpolation. 1. Ingestion points: Command arguments like cluster names and resource groups within SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Interaction with cloud infrastructure through subprocess execution of CLI tools. 4. Sanitization: No explicit validation or escaping is implemented within the skill documentation.
Audit Metadata