skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation describes using inline shell commands (e.g., node -e) to capture repository state, and the evaluation configuration executes a local Node.js script for validation. These are standard development activities.
  • [EXTERNAL_DOWNLOADS]: The metadata.json file contains links to external documentation and a public GitHub repository. These are informational references and do not involve automated code execution or downloads.
  • [SAFE]: The provided JavaScript grader (graders/check-skill.js) is a static analysis tool that reads local files within the skill's workspace to verify metadata formatting. It does not perform network operations or access sensitive system resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 10:17 PM