azure-devops-workitems
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
az boardsCLI andaz restcommands to perform project queries and manage the lifecycle of work items. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it retrieves and processes work item titles and descriptions which can be controlled by external users.
- Ingestion points: Work item details are fetched from Azure DevOps via
az boards queryandaz boards work-item show(SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided for the fetched data.
- Capability inventory: The skill has write access to the environment via
az boards work-item create,az boards work-item update, andaz rest(SKILL.md). - Sanitization: The skill does not perform automated sanitization of external data but mitigates risk by requiring mandatory user confirmation before any destructive or state-changing command is executed.
Audit Metadata