az-cost-optimize
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external files and infrastructure configurations that could theoretically contain malicious instructions intended to influence the AI's issue generation behavior.
- Ingestion points: Infrastructure-as-Code (IaC) files identified via
file_search(Bicep, Terraform, JSON templates) and Azure resource metadata (names, tags) retrieved via discovery tools. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill possesses the capability to write to external systems via GitHub issue creation (
create_issue) and execute shell-based commands for Azure resource management. - Sanitization: No specific data sanitization or escaping is mentioned for the content interpolated into issue templates, although Step 5 requires explicit user confirmation before any issues are created.
- [COMMAND_EXECUTION]: The workflow relies on executing multiple shell commands and MCP tools to interact with the environment.
- Evidence: Utilizes
az resource list,az webapp list,az sql server list, and variousazmcp-*tools to query subscriptions and resources. - [EXTERNAL_DOWNLOADS]: The skill references external resources for configuration and analysis data.
- Evidence: Fetches cost optimization best practices via
azmcp-bestpractices-getand references official Azure pricing documentation athttps://azure.microsoft.com/pricing/to validate estimates.
Audit Metadata