skill-creator

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a local validation script (graders/check-skill.js) which is invoked via Node.js in the eval.yaml workflow. This script performs structural checks on local draft files using regular expressions and does not involve any network activity or unauthorized file system operations.
  • [EXTERNAL_DOWNLOADS]: The metadata.json file references external documentation and an open-source testing framework located at agentskills.io and github.com/mgechev/skillgrade. These resources are consistent with the skill's purpose as an authoring guide and do not represent a remote code execution risk.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:41 AM