Azure DevOps Orchestration
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to its core "Ship Workflow".
- Ingestion points: Requirements, acceptance criteria, and reproduction steps are fetched from Azure DevOps work items via the
az boards work-item showcommand (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or instructions to treat work item content as untrusted.
- Capability inventory: The agent has access to the
Bash,Write, andEdittools, as well as theaz devopsCLI, enabling it to modify the codebase, commit changes, and trigger pipelines (SKILL.md). - Sanitization: No sanitization or validation of the fetched work item data is performed before it is used to generate implementation plans and code.
- [COMMAND_EXECUTION]: The orchestration logic involves extensive use of the
Bashtool to perform git operations (git checkout,git pull,git push), interact with Azure services via theazCLI, and execute local test suites using auto-detected runners such asnpm testorpytest(SKILL.md, references/ship-workflow.md). - [EXTERNAL_DOWNLOADS]: The skill configuration in SKILL.md and references/cross-plugin-patterns.md mentions several MCP servers and packages. These include
@azure/mcp,@microsoft/azure-devops-mcp,@microsoft/powerbi-modeling-mcp, and@playwright/mcp, which are distributed by trusted organizations.
Audit Metadata