azure-test-plans

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill utilizes the Azure CLI (az boards) for test plan and suite management. These are standard administrative actions appropriate for the skill's purpose.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8). \n
  • Ingestion points: Data used to populate System.Title and Microsoft.VSTS.TCM.Steps in the Python script within SKILL.md. \n
  • Boundary markers: Absent; data is directly interpolated into JSON payloads for the Azure DevOps API. \n
  • Capability inventory: Writing/creating work items via requests.post and executing Azure CLI commands (az boards). \n
  • Sanitization: Absent; the script does not escape or validate input strings before API submission.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM