adf-master
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the 'PrePostDeploymentScript.Ver2.ps1' utility from the official Azure/Microsoft GitHub repository. These downloads are pinned to a specific commit hash, which is a security best practice for supply chain integrity.
- [COMMAND_EXECUTION]: The documentation includes various PowerShell and Azure CLI command patterns for deploying ARM templates and managing Azure Data Factory resources. These are standard operations for CI/CD tasks.
- [PROMPT_INJECTION]: The skill defines a workflow that involves fetching external documentation via the 'Context7' MCP tool. This creates an indirect prompt injection surface where untrusted content from the web could potentially influence agent behavior. However, the skill proactively mitigates this risk by including a 'Remote Content Safety' section that instructs the agent to treat fetched data as untrusted, ignore embedded instructions or tool requests, and independently validate all commands before execution.
Audit Metadata