skills/sonvee/ai-skills/skill-creator/Gen Agent Trust Hub

skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs local orchestration by executing its own suite of utility scripts (e.g., run_eval.py, package_skill.py) and the claude CLI. These operations are core to the skill's purpose of automating the skill development lifecycle.
  • [EXTERNAL_DOWNLOADS]: Functionality such as description optimization and frontmatter parsing requires the anthropic and pyyaml Python packages. These are standard, well-known dependencies for LLM application development.
  • [COMMAND_EXECUTION]: The generate_review.py script facilitates result inspection by launching a local HTTP server. It includes logic to manage local processes on the assigned port, which is typical for development-oriented tooling.
  • [EXTERNAL_DOWNLOADS]: The HTML viewer fetches the SheetJS library from a well-known CDN (cdn.sheetjs.com) to enable in-browser rendering of spreadsheet outputs, which is a benign functional requirement for its intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:53 PM