azure-well-architected-review
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as Infrastructure-as-Code (IaC) files and Azure resource metadata. This content could potentially contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: Local IaC files (Bicep, Terraform, ARM templates) and resource information from Azure CLI output.\n
- Boundary markers: The instructions do not define specific delimiters to isolate external code from the agent's internal logic.\n
- Capability inventory: The skill can execute Azure CLI commands and create GitHub issues using the available GitHub MCP server.\n
- Sanitization: No explicit validation or filtering of the processed infrastructure data is described.\n- [EXTERNAL_DOWNLOADS]: The skill retrieves framework guidelines and pillar checklists from official Microsoft documentation domains. This is a neutral operation fetching reference material from a well-known service provider.\n- [COMMAND_EXECUTION]: The workflow utilizes Azure CLI commands to discover resources and evaluate their configurations. These actions are directly aligned with the skill's primary function of performing a cloud architecture audit.
Audit Metadata