skills/lukastk/boxyard/boxyard-cli/Gen Agent Trust Hub

boxyard-cli

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous command-line examples for the boxyard CLI. It explicitly categorizes commands into 'read-only' (safe to run without confirmation) and state-modifying (requires user confirmation), which is a security best practice for agent instructions.
  • [EXTERNAL_DOWNLOADS]: The skill documents the boxyard new --git-clone command, which allows the agent to download content from remote Git repositories. This is a standard feature of the tool and is documented transparently.
  • [DATA_EXFILTRATION]: While the skill facilitates network operations through synchronization (via rclone), this is the primary intended purpose of the tool. The skill documents the location of the rclone configuration file (boxyard_rclone.conf), which may contain sensitive credentials, but it does not instruct the agent to disclose or exfiltrate the contents of this file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 02:40 PM