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

crabbox

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the crabbox CLI and pnpm scripts to execute local environment management commands. It also includes instructions for using sudo on remote hosts to configure system paths during setup.
  • [REMOTE_CODE_EXECUTION]: Facilitates the execution of shell commands and scripts on remote AWS, Blacksmith Testbox, and SSH targets as part of its core remote validation functionality.
  • [EXTERNAL_DOWNLOADS]: References and installs software from vendor-controlled sources associated with 'openclaw' (e.g., openclaw.ai, OpenClaw Homebrew tap) and well-known services like GitHub Actions.
  • [SAFE]: The skill explicitly advises against printing or syncing secrets (e.g., API keys, coordinator tokens) and provides detailed guidance on redacting sensitive information from logs and shell history.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:41 AM
Security Audit — agent-trust-hub — crabbox