skill-creator

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill is designed as an instructional and tool-based framework for creating other agent skills. It contains no instructions that attempt to override system prompts or bypass safety filters.
  • [COMMAND_EXECUTION]: Includes Python utility scripts (init_skill.py, package_skill.py, quick_validate.py) for managing the lifecycle of a skill. These scripts perform standard file system operations such as directory creation, template generation, and ZIP archival.
  • [EXTERNAL_DOWNLOADS]: The documentation mentions external dependencies and tools, such as the claude-skills-cli Node.js package, used for skill validation and packaging. These references are for legitimate development tools and are not executed silently.
  • [SAFE]: Code examples in references/skill-examples.md demonstrate how to use environment variables for authentication (e.g., GITHUB_TOKEN), adhering to security best practices for credential management by not hardcoding secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 07:11 PM
Security Audit — agent-trust-hub — skill-creator