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 boards CLI and az rest commands 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 query and az 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, and az 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
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:45 AM