skill-creator

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Python subprocess module to execute local commands, including the claude CLI and utility scripts for packaging and benchmarking. This is an integral part of the skill's functionality for automating the development and evaluation of other skills.
  • [EXTERNAL_DOWNLOADS]: The eval-viewer component references a CDN-hosted version of the SheetJS library (cdn.sheetjs.com) to enable the rendering of spreadsheet files within the local user interface. This is a well-known service used here for its intended purpose of data visualization.
  • [DYNAMIC_EXECUTION]: The skill dynamically generates command files in the .claude/commands/ directory to test platform triggering logic and populates an HTML template with execution results for user review. These mechanisms are transparently implemented to support the skill's primary objective of optimizing AI agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:08 PM
Security Audit — agent-trust-hub — skill-creator