anthropic-skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill serves as a template and guide for creating structured agent skills. It contains documentation, prompt templates, and checklists that do not pose security risks.
  • [COMMAND_EXECUTION]: The skill includes a local shell script scripts/new_skill.sh for scaffolding project directories. The script implements security best practices by validating the $skill_name input against a restrictive alphanumeric regex, preventing potential command injection or directory traversal attacks.
  • [EXTERNAL_DOWNLOADS]: The skill references an official PDF guide from Anthropic's public resources domain (resources.anthropic.com). This is a trusted source used solely for documentation and does not involve automated execution of remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 03:29 PM