azure-key-vault
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the 'az' and 'jq' utilities to perform administrative operations on Azure Key Vault. Commands include listing resources and managing secrets, which are executed as subprocesses using provided examples.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by processing external tool output. \n- Ingestion points: Data returned from 'az keyvault' commands is piped into 'jq' and processed by the agent. \n- Boundary markers: Not present. \n- Capability inventory: Local execution of 'az' and 'jq' binaries. \n- Sanitization: No filtering or sanitization of the tool output is performed before ingestion.
Audit Metadata