ado-create-task
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill implements a robust defensive guardrail by instructing the agent to disregard any text provided alongside the command, requiring all data to be gathered through controlled interactive prompts.
- [COMMAND_EXECUTION]: Interaction with Azure DevOps is limited to specific MCP tools (wit_get_work_item, wit_add_child_work_items, wit_update_work_item) with no exposure to shell execution or arbitrary command invocation.
- [DATA_EXFILTRATION]: Local configuration (CLAUDE.md) is accessed solely to retrieve organizational identifiers required for the Azure DevOps tools. No sensitive information is exfiltrated to external or untrusted services.
Audit Metadata