azure-finops
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands using the
azCLI for reservation and resource graph queries. It also includes a fallback execution patternuv run python -m azure_finops, which runs a Python module for batch analysis.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Azure resource metadata (names, SKUs, regions) and processes existing files in aPlans/directory to generate reports and responses.\n - Ingestion points: Output from
az graph query,mcp__azure__*tools, and files within thePlans/directory.\n - Boundary markers: The instructions lack specific delimiters or guardrails to prevent the agent from following instructions potentially embedded in resource names or properties.\n
- Capability inventory: The skill can execute shell commands (
az), call Azure-related MCP tools, and write files to the local file system.\n - Sanitization: There is no explicit sanitization step for the data retrieved from Azure before it is used in prompt interpolation or report generation.
Audit Metadata