anthropic-skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a local bash script (scripts/new_skill.sh) used for scaffolding new skill directories. The script validates the user-provided skill name using a regular expression to ensure it follows a kebab-case format, preventing directory traversal via the name parameter.
  • [SAFE]: The skill references official documentation from Anthropic (resources.anthropic.com), which is a recognized and trusted source.
  • [SAFE]: No obfuscation, data exfiltration, or persistence mechanisms were found. The skill operates within its defined purpose of aiding skill development.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 06:39 AM