sub-agent-creator

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a template generator and instructional guide for organizing sub-agent definitions. It does not contain any executable scripts, background processes, or automated commands that could pose a security risk.
  • [SAFE]: The instructions and data files (specifically tools.yaml) demonstrate a strong security posture by categorizing tools by risk level (e.g., 'safe' for read-only vs. 'critical' for Bash) and explicitly recommending that users start with minimal permissions.
  • [SAFE]: No patterns of prompt injection, data exfiltration, or persistence mechanisms were detected. The skill's primary focus is on generating markdown files in standard Claude Code configuration directories.
  • [SAFE]: The skill provides helpful, defensive examples of agent prompts, such as a code reviewer that specifically searches for security vulnerabilities like SQL injection.
  • [SAFE]: External references point exclusively to official Anthropic documentation, providing a trusted source for further learning.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 08:10 AM