azure-cli
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to download an installation script from a well-known Microsoft domain (aka.ms).
- [REMOTE_CODE_EXECUTION]: The installation process involves piping a remote script directly into a shell, which is the official installation method for the Azure CLI tool.
- [PRIVILEGE_ESCALATION]: The setup script uses sudo to acquire necessary permissions for system-wide installation of the CLI tool.
- [INDIRECT_PROMPT_INJECTION]: The skill provides commands that list and query cloud resources, creating a surface where untrusted data (like resource names) could enter the agent context. 1. Ingestion points: Output from 'az group list', 'az vm list', and 'az storage blob list' commands. 2. Boundary markers: No delimiters are specified for the output. 3. Capability inventory: The skill can create and manage VMs, storage containers, and network security rules, and can perform file upload/download operations. 4. Sanitization: No explicit output sanitization is performed in the examples.
Audit Metadata