deployment-pipelines-authoring-cli

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFE
Full Analysis
  • [Standard Administrative Operations]: The skill utilizes az rest and curl to interact with official Fabric API endpoints at api.fabric.microsoft.com. These operations are consistent with administrative management tasks and leverage the user's existing authentication context.
  • [User Confirmation Guardrails]: The instructions explicitly mandate that the agent must confirm destructive intent with the user before executing actions like deleting pipelines, unassigning workspaces, or performing backward deployments, which helps prevent accidental data loss.
  • [Local Data Comparison]: The skill includes a helper script (diff_item_definitions.py) that processes item metadata locally. This script uses Python standard libraries to decode Base64 payloads and normalize identifiers, ensuring that only relevant differences are processed by the agent without relying on external network requests or untrusted dependencies.
  • [Permission Awareness]: The skill provides clear documentation regarding the required delegated scopes and roles (e.g., Pipeline Admin, Workspace Contributor). It instructs the agent to verify these permissions and provide actionable feedback if access is denied, supporting a least-privilege approach.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 01:44 PM
Security Audit — agent-trust-hub — deployment-pipelines-authoring-cli