azure-cost
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: Retrieves Azure cost, billing, and resource metadata via the official Azure Management REST API. This data access is essential for the skill's purpose and uses standard, well-known Microsoft API endpoints.
- [COMMAND_EXECUTION]: Executes standard Azure CLI commands including 'az rest', 'az monitor', and 'az resource' to retrieve performance metrics and infrastructure data. It also leverages the 'azqr' tool for scanning resource compliance.
- [EXTERNAL_DOWNLOADS]: Fetches current pricing information from official Microsoft Azure documentation websites to provide accurate cost optimization and rightsizing recommendations.
- [COMMAND_EXECUTION]: Generates Azure CLI commands and Resource Graph queries dynamically based on user intent using helper tools. It manages temporary JSON configuration files for API request bodies and ensures their deletion after processing.
- [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface as it ingests data from external sources during analysis.
- Ingestion points: Documentation search results, pricing webpages, and Azure API responses containing resource metadata.
- Boundary markers: The instructions do not specify explicit delimiters or markers to isolate ingested external content from internal prompts.
- Capability inventory: Includes shell command execution via Azure CLI, report generation via file writes, and temporary file cleanup.
- Sanitization: The skill does not define specific sanitization or validation routines for the data processed from external sources.
Audit Metadata