azure-cost-optimization
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the azqr (Azure Quick Review) utility and retrieves pricing data from official Microsoft Azure domains (azure.microsoft.com). These resources originate from trusted organizations and well-known services.
- [COMMAND_EXECUTION]: The skill utilizes Azure CLI commands and PowerShell scripts to query resource configurations, costs, and utilization metrics. These operations are necessary for the skill's primary purpose of cloud infrastructure analysis and are structured around diagnostic and reporting tasks.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests external data from Azure APIs and web pages and incorporates it into generated reports without validation.
- Ingestion points: Data is retrieved via Azure Resource Graph, Cost Management APIs, and the fetch_webpage tool, which includes potentially attacker-controlled resource tags and metadata.
- Boundary markers: The instructions for generating the optimization report do not include specific delimiters or warnings to the agent to ignore or isolate instructions embedded in the retrieved metadata.
- Capability inventory: The skill can create and delete files (create_file, Remove-Item) and interact with Azure Management APIs (az rest, az monitor).
- Sanitization: No logic is implemented to sanitize or escape resource metadata or web content before it is used to populate the generated Markdown reports.
Audit Metadata