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
Bashtool andbypassPermissionsmode. 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