skills/olcubo/cubox-cli/cubox/Gen Agent Trust Hub

cubox

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to update the cubox-cli tool and skill metadata via NPM and vendor-specific repositories. These resources originate from the verified author and well-known services.
  • [COMMAND_EXECUTION]: All bookmark management is performed using the cubox-cli binary. The skill implements a dry-run policy for deletions to ensure user oversight and prevent accidental data loss.
  • [DATA_EXFILTRATION]: The skill handles user reading data and provides clear directives to keep authentication tokens secure and private, minimizing the risk of credential leakage.
  • [SAFE]: Analysis of the instructions and references revealed no evidence of prompt injection, obfuscation, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 03:22 PM