anthropic-skill-creator

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides documentation, templates, and guidelines for building AI agent skills based on established best practices.
  • [COMMAND_EXECUTION]: The skill includes a local shell script (scripts/new_skill.sh) used to scaffold new skill directories. The script implements input validation using a regular expression to ensure skill names follow a specific format, which mitigates potential shell injection risks during directory creation and file generation.
  • [EXTERNAL_DOWNLOADS]: References official documentation hosted on Anthropic's resource domain. This is a static link for informational purposes and does not involve the execution of remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 12:53 AM