arkcli-onboard

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a high-level orchestration layer for the 'arkcli' tool, which is a resource owned by the vendor (volcengine). It does not contain any direct malicious code or unexpected network operations.
  • [SAFE]: It explicitly enforces security 'gates,' requiring the agent to verify authentication status and real-name registration (via shared references) before proceeding with deployment tasks.
  • [SAFE]: The workflow incorporates mandatory human-in-the-loop confirmation for write operations. It specifies that the agent must provide a read-only preview and obtain explicit user consent before creating endpoints.
  • [SAFE]: The skill defines clear boundaries and anti-trigger rules to prevent the misuse of the CLI for unsupported model types (such as voice models), directing users to discovery tools instead.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 04:04 PM
Security Audit — agent-trust-hub — arkcli-onboard