azure-cost
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Azure CLI (az), Resource Graph (az graph), and Kubernetes (kubectl) tools to perform cost analysis and resource discovery. These are standard administrative actions aligned with the skill's purpose.
- [DATA_EXPOSURE]: The skill emphasizes the use of managed identities and Azure RBAC for authentication, explicitly warning against hardcoded credentials in production environments.
- [EXTERNAL_DOWNLOADS]: The skill references and fetches content from official Microsoft Azure domains and documentation, which are trusted sources and do not introduce remote code execution risks.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Azure API responses and pricing pages.
- Ingestion points: API responses from az rest and az graph (cost-query/workflow.md, cost-optimization/workflow.md), and web content from azure.microsoft.com via fetch_webpage (cost-optimization/workflow.md).
- Boundary markers: None identified in the prompt instructions to isolate external data.
- Capability inventory: Execution of CLI commands (az, kubectl) and file management (create_file).
- Sanitization: No explicit sanitization of external data is defined before processing or reporting.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected.
Audit Metadata