create-subagent

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation, templates, and best practices for creating subagents. Analysis of the content reveals no prompt injection attempts, malicious obfuscation, or unauthorized data access.
  • [COMMAND_EXECUTION]: The documentation explicitly describes the use of the Bash tool and bypassPermissions mode. While these represent high-privilege capabilities within the Claude Code system, the skill includes appropriate warnings regarding their risk and advocates for the principle of least privilege.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:48 AM