Azure DevOps Boards

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides documentation for using the Bash tool to execute Azure DevOps CLI (az devops) commands and curl for interacting with the REST API. This is the primary intended function of the skill for project management automation.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets were found. Code and script examples correctly reference environment variables (e.g., $ADO_PAT) for handling Personal Access Tokens.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it facilitates reading work item titles, descriptions, and comments which are untrusted external inputs.
  • Ingestion points: Work item fields (Title, Description, History) fetched via _apis/wit/workitems as documented in references/work-items-boards.md.
  • Boundary markers: None; the skill does not instruct the agent to use specific delimiters when processing work item content.
  • Capability inventory: The skill allows Bash execution and file Write/Edit operations.
  • Sanitization: No sanitization or validation logic for the retrieved work item data is described in the reference material.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 03:34 AM
Security Audit — agent-trust-hub — Azure DevOps Boards