skills/openclaw/mcporter/crabbox/Gen Agent Trust Hub

crabbox

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents usage of the crabbox CLI and associated tools to perform remote operations. This includes local command execution to trigger remote tasks, environment setup, and cleanup.
  • [EXTERNAL_DOWNLOADS]: Instructions include downloading the vendor's CLI tool via Homebrew and interacting with a centralized coordination service at https://crabbox.openclaw.ai for authentication and lease management.
  • [SAFE]: The documentation explicitly warns against unsafe practices like printing API keys or including them in remote logs, directing the user to use secure environment forwarding instead.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:46 AM
Security Audit — agent-trust-hub — crabbox