create-agent-skills

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides extensive documentation on security best practices, specifically addressing the prevention of credential leakage in chat history by recommending wrapper scripts and environment variables for API calls.
  • [SAFE]: It includes advanced safety guidance for skill authors, such as using specific syntax (adding spaces) to prevent the unintentional execution of dynamic context commands while the agent is reading documentation.
  • [COMMAND_EXECUTION]: The skill uses standard shell commands (ls, mkdir, cat, chmod) to manage the .claude/skills/ and .claude/commands/ directories. These operations are essential for its stated purpose as a development and management tool for agent skills.
  • [EXTERNAL_DOWNLOADS]: The instructions reference well-known package managers (pip, npm) and official documentation sources (Claude Code docs, Anthropics GitHub). These references are informative and adhere to trusted source guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 05:14 PM